The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Objects365: A Large-Scale, High-Quality Dataset for Object Detection
Abstract
In this paper, we introduce a new large-scale object detection dataset, Objects365, which has 365 object categories over 600K training images. More than 10 million, high-quality bounding boxes are manually labeled through a three-step, carefully designed annotation pipeline. It is the largest object detection dataset (with full annotation) so far and establishes a more challenging benchmark for the community. Objects365 can serve as a better feature learning dataset for localization-sensitive tasks like object detection and semantic segmentation. The Objects365 pre-trained models significantly outperform ImageNet pre-trained models with 5.6 points gain (42 vs 36.4) based on the standard setting of 90K iterations on COCO benchmark. Even compared with much long training time like 540K iterations, our Objects365 pretrained model with 90K iterations still have 2.7 points gain (42 vs 39.3). Meanwhile, the finetuning time can be greatly reduced (up to 10 times) when reaching the same accuracy. Better generalization ability of Object365 has also been verified on CityPersons, VOC segmentation, and ADE tasks. The dataset as well as the pretrained-models have been released at www.objects365.org.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Existing large DETR models [3, 6, 32, 41, 44, 46] have demonstrated impressive performance on COCO test-dev [20] leaderboard.”
From DETRs Beat YOLOs on Real-time Object Detection (2024) · cites this paper as [32]
In the citing paper
“In contrast, DINO achieves the SOTA result with a publicly available SwinL [23] backbone and a public dataset Objects365 [33] (1.7M annotated images) only.”
From DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection (2022) · cites this paper as [33]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Self-citationImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581
Flagged first, then by citations
Research works printed but not linked: 3
- girshick, 2018, Detectron
- he, 2018, Rethinking im-agenet pre-training, arXiv preprint arXiv 1811 08883
- everingham, 0, The PASCAL Visual Object Classes Challenge 2012 (VOC2012) Results
Cited by
Sorted by citations
DETRs Beat YOLOs on Real-time Object Detection
Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., & Chen, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01605 · Cited by 5,020
“After pre-training with Objects365 [32], RT-DETR-R50 / R101 achieves 55 .”
Object Detection in 20 Years: A Survey
Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3238524 · Cited by 3,689
“, ILSVRC2014) [56], MS-COCO Detection Challenge [57], Open Images Dataset [58, 59], Objects365 [60], etc.”
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
Terven, J. R., Esparza, D. M. C., & Romero-González, J.-A. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5040083 · Cited by 4,118
“The model is pre-trained on Objects365 [126], which contains two million images and 365 categories, then the COCO dataset was used to generate pseudo-labels.”
MethodSwin Transformer V2: Scaling Up Capacity and Resolution
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et al. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01170 · Cited by 2,985
“For our largest model experiments, we employ an additional detection pre-training phase using Object 365 v2 dataset [59], in-between the image classification pre-training phase and the COCO fine-tuning phase.”
MethodSwin Transformer V2: Scaling Up Capacity and Resolution
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.09883 · Cited by 2,679
“For our largest model experiments, we employ an additional detection pre-training phase using Object 365 v2 dataset [59], in-between the image classification pre-training phase and the COCO fine-tuning phase.”
MethodGrounding DINO: Marrying DINO with Grounded Pre-training for Open-Set Object Detection
Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Jiang, Q., Li, C., Yang, J., Su, H., et al. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72970-6_3 · Cited by 2,074
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., & Zhao, H. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00987 · Cited by 1,296
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
Ghiasi, G., Cui, Y., Srinivas, A., Qian, R., Lin, T.-Y., Cubuk, E. D., Le, Q. V., & Zoph, B. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00294 · Cited by 1,324
“When combined with self-training using unlabeled COCO and unlabeled Objects365 [49] for pseudo-labeling, we see a further improvement of 2.5 box AP and 2.2 mask AP, resulting in a model with a strong performance of 57.3 box AP and 49.1 mask AP on COCO test-dev without test-time augmen-tations and model ensembling.”
MethodInfluentialGrounded Language-Image Pre-training
Li, L. H., Zhang, P., Zhang, H., Yang, J., Li, C., Zhong, Y., Wang, L., Yuan, L., Zhang, L., Hwang, J., et al. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01069 · Cited by 1,336
“, Objects365 [47]), in practice, we can split the categories into multiple prompts during training and inference.”
BackgroundMethodInternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01385 · Cited by 1,080
“For this dataset, we initialize our InternImage-H with the Objects365 [79]”
MethodInfluentialSelf-citationVision-Language Models for Vision Tasks: A Survey
Zhang, J., Huang, J., Jin, S., & Lu, S. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3369699 · Cited by 1,051
“With the object locating ability learned from auxiliary datasets [85], [86], pre-trained VLMs achieve zero-shot prediction for object detection tasks by comparing the embeddings of the given object proposals and texts.”
BackgroundMethodVinVL: Revisiting Visual Representations in Vision-Language Models
Zhang, P., Li, X., Hu, X., Yang, J., Zhang, L., Wang, L., Choi, Y., & Gao, J. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00553 · Cited by 1,015
“3 mAP 50 in [30], which is obtained by pre-training on Objects365.”
BackgroundMethodYOLO-World: Real-Time Open-Vocabulary Object Detection
Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., & Shan, Y. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01599 · Cited by 815
“For pre-training YOLO-World, we mainly adopt detection or grounding datasets including Ob-jects365 (V1) [46], GQA [18], Flickr30k [38], as specified in Tab.”
MethodDINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L. M., & Shum, H.-Y. (2022) · arXiv · Cited by 1,154
“DINO with ResNet-50 is trained on train2017 without extra data, while DINO with SwinL is first pre-trained on Object365 [33] and then fine-tuned on train2017.”
BackgroundMethodInfluentialDETRs with Collaborative Hybrid Assignments Training
Zong, Z., Song, G., & Liu, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00621 · Cited by 725
“Then we perform intermediate finetuning on the Objects365 dataset us-ing C o-DINO-Deformable-DETR for 26 epochs and reduce the learning rate by a factor of 0.1 at epoch 24.”
MethodInfluentialImbalance Problems in Object Detection: A Review
Öksüz, K., Çam, B. C., Kalkan, S., & Akbaş, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2981890 · Cited by 629
“Throughout the text, unless otherwise specified, “COCO”, “PASCAL”, and “Open Images” respectively correspond to the Pascal VOC 2012 trainval [51], MS-COCO 2017 train [90], Open Images v5 training (subset with bounding boxes) [91] and Objects365 train [92] dataset partitions.”
BackgroundGLIGEN: Open-Set Grounded Text-to-Image Generation
Li, Y., Liu, H., Wu, Q., Mu, F., Yang, J., Gao, J., Li, C., & Lee, Y. J. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02156 · Cited by 715
“Specifically, we follow GLIP [34] and train on Object365 [58] and GoldG [34], which combines two grounding datasets: Flickr [49] and VG [31].”
End-to-End Semi-Supervised Object Detection with Soft Teacher
Xu, M., Zhang, Z., Hu, H., Wang, J., Wang, L., Wei, F., Bai, X., & Liu, Z. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00305 · Cited by 609
“* indicates that models are pre-trained with Object365 [24] dataset.”
BackgroundMethodInfluentialMask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation
Li, F., Zhang, H., Xu, H., Liu, S., Zhang, L., Ni, L. M.-S., & Shum, H. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00297 · Cited by 662
“After detection pre-training on the Objects365 [31] dataset with a SwinL [24] backbone, Mask DINO significantly improves all segmentation tasks and achieves the best results on instance ( 54.5 AP on COCO), panoptic ( 59.4 PQ on COCO), and semantic ( 60.8 mIoU on ADE20K) segmentation among models under one billion param…”
BackgroundMethodInfluentialDetecting Twenty-Thousand Classes Using Image-Level Supervision
Zhou, X., Girdhar, R., Joulin, A., Krähenbühl, P., & Misra, I. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20077-9_21 · Cited by 564
“We evaluate on two large-scale object detection datasets: Objects365v2 [44] and OpenImages [25], both with around 1.8M training images.”
BackgroundMethodInfluentialSun, X., Wang, P., Yan, Z., Xu, F., Wang, R., Diao, W., Chen, J., Li, J., Feng, Y., Xu, T., et al. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.12.004 · Cited by 608
“More recently, Megvii released Objects365 [46], a largescale dataset containing 638k images, which is 5 times larger than MSCOCO dataset.”
MethodSelf-citationImage as a Foreign Language: BEIT Pretraining for Vision and Vision-Language Tasks
Wang, W., Bao, H., Dong, L., Bjorck, J., Peng, Z., Liu, Q., Aggarwal, K., Mohammed, O. K., Singhal, S., Som, S., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01838 · Cited by 561
“Following common practices [39, 72], we first conduct intermediate finetuning on the Objects365 [51] dataset.”
MethodEVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Fang, Y., Wang, W., Xie, B., Sun, Q., Wu, L., Wang, X., Huang, T., Wang, X., & Cao, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01855 · Cited by 655
“For intermediate fine-tuning on Objects365 [87], the model is trained with a batch size of 128 for 380k iterations.”
MethodInfluentialRethinking Pre-training and Self-trainingPreprint
Zoph, B., Ghiasi, G., Lin, T.-Y., Cui, Y., Liu, H., Cubuk, E. D., & Le, Q. V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06882 · Cited by 579
“Note that OID is found to not be helpful on COCO by pre-training in [41].”
BackgroundYOLO-based Object Detection Models: A Review and its Applications
Vijayakumar, A., & Subramaniyaswamy, V. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18872-y · Cited by 562
“[24] The effectiveness and generalizability of the resulting computer vision models are strongly influenced by the quality and diversity of the data that was gathered.”
Open-vocabulary Object Detection via Vision and Language Knowledge DistillationPreprint
Gu, X.-Y., Lin, T.-Y., Kuo, W.-C., & Cui, Y. (2021) · International Conference on Learning Representations · doi:10.48550/arxiv.2104.13921 · Cited by 1,464
“We evaluate the transferability of ViLD on PASCAL VOC (Everingham et al., 2010), COCO (Lin et al., 2014), and Objects365 (Shao et al., 2019).”
MethodInfluentialAli, M. L., & Zhang, Z. (2024) · Computers · doi:10.3390/computers13120336 · Cited by 383
“However, the architectural advancements in YOLOv10 and YOLOv11 resulted in even better performance, with YOLOv11 achieving an mAP50 of 0.958.”
InfluentialLearning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model
Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., & Li, G. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01369 · Cited by 393
“Meanwhile, we conduct transfer experiments to demonstrate generalization ability of our approach, and evaluate our LVIS-trained model on Pascal VOC [4] test set, COCO [15] validation set and Objects365 [23] validation set.”
MethodSimple Open-Vocabulary Object Detection
Minderer, M., Gritsenko, A. A., Stone, A., Neumann, M., Weissenborn, D., Dosovitskiy, A., Mahendran, A., Arnab, A., Dehghani, M., Shen, Z., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20080-9_42 · Cited by 406
How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites
Chen, Z., Wang, W., Tian, H., Ye, S., Gao, Z., Cui, E., Tong, W., Hu, K., Luo, J., Ma, Z., et al. (2024) · Science China Information Sciences · doi:10.1007/s11432-024-4231-5 · Cited by 1,058
“Detection and grounding tasks utilize datasets like Ob-jects365 [93], GRIT [86], and All-Seeing [114], making up 5.2%.”
InfluentialFlorence-2: Advancing a Unified Representation for a Variety of Vision Tasks
Xiao, B., Wu, H., Xu, W., Dai, X., Hu, H., Lu, Y., Zeng, M., Liu, C., & Yuan, L. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00461 · Cited by 459
“In addition, our dataset has around 1.3B region-text annotations, which is more than 30x larger than the academic object detection datasets such as OpenImages [40] and Object 365 [70].”
BackgroundMethodExploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
Wang, S., Liu, Y., Wang, T., Li, Y., & Zhang, X. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00335 · Cited by 292
“Following BEVFormerv2 [50], the ViT-Large [8] is pre-trained on Objects365 [41] and COCO [28] dataset.”
MethodSelf-citationBeyond Bounding-Box: Convex-hull Feature Adaptation for Oriented and Densely Packed Object Detection
Guo, Z., Liu, C., Zhang, X., Jiao, J., Ji, X., & Ye, Q. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00868 · Cited by 271
“This is attributed to the availability of deep networks incorporating rich feature representation [16, 15] and large-scale databases [3, 17, 28] for pretraining representative models.”
BackgroundSelf-citationGroup DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
Chen, Q., Chen, X., Wang, J., Zhang, S., Yao, K., Feng, H., Han, J., Ding, E., Zeng, G., & Wang, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00610 · Cited by 304
“We follow its training pipeline and settings: (i) pre-train [5] and fine-tune the ViT-Huge on ImageNet-1K [8], (ii) pre-train the whole detector on Object365 [22] for 24 epochs with 64 A100 GPUs, and (iii) finetune the detector on COCO [15] for 20 epochs with 32 A100 GPUs.”
MethodTransformer-Based Visual Segmentation: A Survey
Li, X., Ding, H., Yuan, H., Zhang, W., Pang, J., Cheng, G., Chen, K., Liu, Z., & Loy, C. C. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3434373 · Cited by 305
“However, due to the extra datasets [352] they used, we do not list them here.”
BackgroundS2Looking: A Satellite Side-Looking Dataset for Building Change Detection
Shen, L., Lu, Y., Chen, H., Wei, H., Xie, D., Yue, J., Chen, R., Lv, S., & Jiang, B. (2021) · Remote Sensing · doi:10.3390/rs13245094 · Cited by 259
“These include ImageNet [39], COCO [40], PIE [41], MVTec AD [42], Objects365[43], WildDeepfake [44], FineGym [45] and ISIA Food-500 [46].”
MethodKhanam, R., Hussain, M., Hill, R. C., & Allen, P. (2024) · IEEE Access · doi:10.1109/access.2024.3425166 · Cited by 296
“More recent contributions such as Objects365 [236] have further emphasized the importance of temporal dynamics and object interactions in OD tasks.”
BackgroundTransfer learning for medical images analyses: A survey
Yu, X., Wang, J., Hong, Q., Teku, R., Wang, S., & Zhang, Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.08.159 · Cited by 241
AutoAssign: Differentiable Label Assignment for Dense Object DetectionPreprint
Zhu, B., Wang, J., Jiang, Z., Zong, F., Liu, S., Li, Z., & Sun, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03496 · Cited by 274
“Extensive experiments with competitive results are carried out on the challenging MS COCO [12] dataset and other datasets from different domains, such as PASCAL VOC [3, 4], Object365 [19] and Wider-Face [22], demonstrating the effectiveness and broad applicability of AutoAssign.”
BackgroundMethodSelf-citationCut and Learn for Unsupervised Object Detection and Instance Segmentation
Wang, X., Girdhar, R., Yu, S. X., & Misra, I. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00305 · Cited by 226
How Much Can CLIP Benefit Vision-and-Language Tasks?Preprint
Shen, S., Li, L. H., Tan, H. X., Bansal, M., Rohrbach, A., Chang, K.-W., Yao, Z., & Keutzer, K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.06383 · Cited by 382
“VinVL (Li et al., 2020) is an extreme scaleup of the region-based paradigm, which is pretrained on multiple object detection datasets, including MS COCO (Lin et al., 2014), OpenImages (Kuznetsova et al., 2020), Object365 (Shao et al., 2019), and Visual Genome (Krishna et al., 2017).”
MethodWu, T., Zhang, J., Fu, X. Y., Wang, Y., Ren, J., Pan, L., Wu, W., Yang, L., Wang, J., Qian, C., et al. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00084 · Cited by 246
GLaMM: Pixel Grounding Large Multimodal Model
Rasheed, H., Maaz, M., Shaji, S., Shaker, A., Khan, S., Cholakkal, H., Anwer, R. M., Xing, E. P., Yang, M., & Khan, F. S. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01236 · Cited by 302
“Images Regions Concepts Tokens Captions † COCO [25] 0.1M 0.9M 80 - - LVIS [9] 0.1M 1.5M 1,203 - - Objects365 [42] 0.6M 10.1M 365 - - Open Images [20] 1.5M 14.8M 600 - - BigDetection [4] 3.5M 36.0M 600 - - V3Det [43] 0.2M 1.5M Table 2.”
Tools, techniques, datasets and application areas for object detection in an image: a review
Kaur, J., & Singh, W. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13153-y · Cited by 212
“Most of the dataset has contained the images downloaded from the “Flickr photo-sharing website” [35, 155].”
MethodProbabilistic two-stage detectionPreprint
Zhou, X., Koltun, V., & Krähenbühl, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.07461 · Cited by 219
“In fact, they are no longer faster than their two-stage counterparts if the vocabulary (i.e., the set of object classes) is large (as in the LVIS or Objects365 datasets).”
BackgroundMethodInfluentialA Survey on Long-Tailed Visual Recognition
Yang, L., Jiang, H., Song, Q., & Guo, J. H. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01622-8 · Cited by 179
“10 (Object365 [133] and ADE20K [201]), and evaluate their performance to investigate whether the long-tailed problem is practically shown in visual recognition.”
BackgroundMethodInfluentialVision-Language Pre-Training: Basics, Recent Advances, and Future Trends
Gan, Z., Li, L., Li, C., Wang, L., Liu, Z., & Gao, J. (2022) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000105 · Cited by 155
GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features
Nguyen, V.-Q., Suganuma, M., & Okatani, T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20059-5_10 · Cited by 152
UniVTG: Towards Unified Video-Language Temporal Grounding
Lin, K. Q., Zhang, P., Chen, J., Pramanick, S., Gao, D., Wang, A. J., Yan, R., & Shou, M. Z. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00262 · Cited by 192
“The emergence of large-scale vision-language datasets, such as [43, 41, 28, 4], has paved the way for the development of VLP [36, 22, 19, 34, 21] to enhance video-text representation for various vision-language tasks [60, 54, 53].”
BackgroundUniversal Instance Perception as Object Discovery and Retrieval
Yan, B., Jiang, Y., Wu, J., Wang, D., Luo, P., Yuan, Z., & Lu, H. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01471 · Cited by 174
“Since Objects365 does not have mask annotations, we introduce two auxiliary losses proposed by BoxInst [97] for training the mask branch.”
BackgroundMethodInfluentialAligning Bag of Regions for Open-Vocabulary Object Detection
Wu, S., Zhang, W., Jin, S., Liu, W., & Loy, C. C. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01464 · Cited by 155
“We transfer the openvocabulary detector trained on OV-LVIS to three other datasets, including Pascal VOC 2007 [11] test set, COCO [31] validation set and Objects365 [43] v2 validation set.”
MethodMultimodal Foundation Models: From Specialists to General-Purpose Assistants
Li, C., Gan, Z., Yang, Z., Yang, J., Li, L., Wang, L., & Gao, J. (2024) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000110 · Cited by 331
A Simple Framework for Open-Vocabulary Segmentation and Detection
Zhang, H., Li, F., Zou, X., Liu, S., Li, C., Yang, J., & Zhang, L. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00100 · Cited by 185
“For object detection, we use Objects365 [42] (660k images for v1 and 1700k images for v2).”
MethodInfluentialInjecting Semantic Concepts into End-to-End Image Captioning
Fang, Z., Wang, J., Hu, X., Liang, L., Gan, Z., Wang, L., Yang, Y., & Liu, Z. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01748 · Cited by 146
“To test the generalization of ViTCAP, we also report the performances on nocaps dataset [1], a benchmark consisting of 166 k human-generated captions describing 15 k images in the wild collected from the OpenImages dataset [60].”
MethodReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension
Subramanian, S., Merrill, W., Darrell, T., Gardner, M., Singh, S., & Rohrbach, A. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.357 · Cited by 172
RT-DETRv3: Real-Time End-to-End Object Detection with Hierarchical Dense Positive Supervision
Wang, S., Xia, C., Lv, F., & Shi, Y. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00166 · Cited by 159
“For example, our RT-DETRv3-R101 can achieve 54.6 AP, which is better than YOLOv10-X.”
InfluentialAffordance Transfer Learning for Human-Object Interaction Detection
Hou, Z., Yu, B., Qiao, Y., Peng, X., & Tao, D. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00056 · Cited by 133
“In detail, we select objects that are labeled as COCO classes from Object365 validation dataset to evaluate the affordance recognition of objects on new domain.”
BackgroundMethodInfluentialLearning Open-World Object Proposals Without Learning to Classify
Kim, D., Lin, T.-Y., Angelova, A., Kweon, I. S., & Kuo, W. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3146922 · Cited by 131
“Therefore, in this work we study the generalization setting of training on COCO, then testing on other datasets: RoboNet [15], Objects365 [48], EpicKitchens [14], and LVIS [24].”
MethodInfluentialDiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
Lan, S., Yu, Z., Choy, C., Radhakrishnan, S., Liu, G., Zhu, Y., Davis, L. S., & Anandkumar, A. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00339 · Cited by 114
“Our weakly supervised design allows D ISCO B OX to be conveniently trained like any object detection algo-rithm on the increasingly large datasets [58–60], but output additional predictions beyond just bounding boxes.”
BackgroundContextual Object Detection with Multimodal Large Language Models
Zang, Y., Li, W., Han, J., Zhou, K., & Loy, C. C. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02214-4 · Cited by 178
“However, these evaluations still rely on the predefined ID-name mappings, while objects with names not included in predefined mappings are impossible.”
A Generalist Framework for Panoptic Segmentation of Images and Videos
Chen, T., Li, L., Saxena, S., Hinton, G. E., & Fleed, D. J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00090 · Cited by 136
“The image encoder is taken from the Pix2Seq [10] object detection checkpoint, pre-trained on objects365 [49].”
MethodWang, R., Liu, L., Xie, C., Yang, P., Li, R., & Zhou, M. (2021) · Sensors · doi:10.3390/s21051601 · Cited by 105
“The current large volume of standardized object detection datasets [1–3] help to explore many key research challenges that are related to object detection and evaluate the performance of different algorithms and technologies.”
BackgroundFlexiViT: One Model for All Patch Sizes
Beyer, L., Izmailov, P., Kolesnikov, A., Caron, M., Kornblith, S., Zhai, X., Minderer, M., Tschannen, M., Alabdulmohsin, I., & Pavetic, F. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01393 · Cited by 132
“8 [48] Shuai Shao, Zeming Li, Tianyuan Zhang, Chao Peng, Gang Yu, Xiangyu Zhang, Jing Li, and Jian Sun.”
BackgroundMethodProposal Learning for Semi-Supervised Object Detection
Tang, P., Ramaiah, C., Wang, Y., Xu, R., & Xiong, C. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00234 · Cited by 101
“However, training accurate object detectors relies on the availability of large scale labeled datasets [9, 29, 40, 42], which are very expensive and time-consuming to collect.”
BackgroundFashionVLP: Vision Language Transformer for Fashion Retrieval with Feedback
Goenka, S., Zheng, Z., Jaiswal, A., Chada, R., Wu, Y., Hedau, V., & Natarajan, P. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01371 · Cited by 109
“We use a publicly available [54] Faster-RCNN-C4 [39] with ResNeXt-152 [52] backbone (X152-C4) trained on MSCOCO [29], Visual Genome [23], Objects365 [43], and OpenImage V5 [24], following [54].”
MethodDetecting Everything in the Open World: Towards Universal Object Detection
Wang, Z., Li, Y., Chen, X., Lim, S.-N., Torralba, A. B., Zhao, H., & Wang, S. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01100 · Cited by 111
“However, if we further add OpenImages images to COCO and Objects365, the LVIS v0.”
InfluentialExploiting Unlabeled Data with Vision and Language Models for Object Detection
Zhao, S., Zhang, Z.-X., Schulter, S., Zhao, L., Kumar, B. G. V., Stathopoulos, A., Chandraker, M. K., & Metaxas, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20077-9_10 · Cited by 104
PANDA: A Gigapixel-Level Human-Centric Video Dataset
Wang, X., Zhang, X., Zhu, Y., Guo, Y., Yuan, X., Xiang, L., Wang, Z., Ding, G., Brady, D. J., Dai, Q., et al. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00333 · Cited by 107
Self-citationConfidence Score: The Forgotten Dimension of Object Detection Performance Evaluation
Wenkel, S., Alhazmi, K., Liiv, T., Alrshoud, S. R., & Simón, M. (2021) · Sensors · doi:10.3390/s21134350 · Cited by 108
“However, benchmark datasets used in publications are not growing despite a growing number of datasets covering the task of 2D (e.g., [12–16]) and 3D object detection (e.g., [17–23]).”
BackgroundActive Teacher for Semi-Supervised Object Detection
Mi, P., Lin, J., Zhou, Y., Shen, Y., Luo, G., Sun, X., Cao, L., Fu, R., Xu, Q., & Ji, R. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01408 · Cited by 100
“Recent years have witnessed the rapid development of object detection supported by a flurry of benchmark datasets [9, 11, 22, 32] and methods [13–15, 23, 26, 28, 29].”
Simple Multi-dataset Detection
Zhou, X., Koltun, V., & Krähenbühl, P. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00742 · Cited by 98
“Yet object detection is fragmented into datasets [18, 22, 24, 33] and our models are locked into the corresponding domains.”
BackgroundMethodInfluentialChen, W., Luo, J., Zhang, F., & Tian, Z. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17949-4 · Cited by 103
Segment and Recognize Anything at Any Granularity
Li, F., Zhang, H., Sun, P., Zou, X., Liu, S., Li, C., Yang, J., Zhang, L., & Gao, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73195-2_27 · Cited by 89
“Generic object detection and segmentation have led to the development of abundant datasets, such as MSCOCO [39], LVIS [21], Objects365 [53], PAS-CAL [15],CityScapes [12],ADE20k [68].”
InfluentialOpen-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling
Huynh, D., Kuen, J., Lin, Z., Gu, J., & Elhamifar, E. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00689 · Cited by 92
“To demonstrate the scalability of our method, we apply cross-modal pseudo-labeling with multiple segmentation datasets (Open Images [2], LVIS [3]), object detection dataset (Objects365 [103]), and caption dataset (Conceptual Captions [99]), to create a high-performance student model.”
MethodClass-Agnostic Object Detection with Multi-modal Transformer
Maaz, M., Rasheed, H., Khan, S. H., Khan, F. S., Anwer, R. M., & Yang, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20080-9_30 · Cited by 87
“Settings: Table 1 shows the object proposal generation performance of MViTs with the typical bottom-up approaches and the end-to-end supervised deep learning methods on five challenging natural image OD datasets (Pascal VOC [14], MS COCO [40], KITTI [17], Objects365 [56] and LVIS [19]).”
MethodOpen Vocabulary Object Detection with Pseudo Bounding-Box Labels
Gao, M., Chen, X., Niebles, J. C., Li, J., Xu, R., Liu, W., & Xiong, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20080-9_16 · Cited by 95
“Therefore, we evaluate our method and the strongest baseline (both are fine-tuned using COCO base classes) on PASCAL VOC [5] test set, Objects365 v2 [25] validation set and LVIS [10] validation set 1.”
MethodSelf-citationRegion-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
Kim, D., Angelova, A., & Kuo, W. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01072 · Cited by 85
“• Objects365 [5]: Custom (research-only, noncommercial)”
Diffusioninst: Diffusion Model for Instance Segmentation
Gu, Z., Chen, H., & Xu, Z. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447191 · Cited by 115
“This section compares our model with popular existing meth-ods and the performances are all obtained without pretraining on extra data like Objects-365 [24].”
MethodA Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future
Zhu, C., & Chen, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3413013 · Cited by 108
DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment
Yao, L., Han, J., Liang, X., Xu, D., Zhang, W., Li, Z., & Xu, H. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02250 · Cited by 94
“Specifically, for detection data, we use a sampled subset from Objects365v2 [43] dataset (denoted as O365) with 0.”
MethodSelf-citationOMG-Seg: Is One Model Good Enough for all Segmentation?
Li, X., Yuan, H., Li, W., Ding, H., Wu, S., Zhang, W., Li, Y., Chen, K., & Loy, C. C. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02640 · Cited by 83
“* denotes models are pre-trained on the Object365 dataset [73].”
Relation DETR: Exploring Explicit Position Relation Prior for Object Detection
Hou, X., Liu, M., Zhang, S., Wei, P., Chen, B., & Lan, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72973-7_6 · Cited by 90
XAIR: A Framework of Explainable AI in Augmented Reality
Xu, X., Yu, A., Jonker, T. R., Todi, K., Lu, F., Qian, X., Belo, J. M. E., Wang, T., Li, M., Mun, A., et al. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581500 · Cited by 96
“For ingredient recognition, we trained a vision-based object detection model that was a variant of the Vision Transformer from CLIP [173] on the LVIS [95] and Objects365 [197] datasets.”
MethodSelf-citationPACO: Parts and Attributes of Common Objects
Ramanathan, V., Kalia, A., Petrovic, V., Wen, Y., Zheng, B., Guo, B., Wang, R., Marquez, A., Kovvuri, R., Kadian, A., et al. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00690 · Cited by 79
“Object detection and segmentation datasets The task of detecting and segmenting object instances is well studied with popular benchmark datasets such as COCO [32], LVIS [15], Object365 [40], Open Images [26] and Pascal [9] for common objects.”
BackgroundPartImageNet: A Large, High-Quality Dataset of Parts
He, J., Yang, S., Yang, S., Kortylewski, A., Yuan, X., Chen, J.-N., Liu, S., Yang, C., Yu, Q., & Yuille, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20074-8_8 · Cited by 105
“Objects365: A large-scale, high-quality dataset for object detection.”
MethodX2-VLM: All-in-One Pre-Trained Model for Vision-Language Tasks
Zeng, Y., Zhang, X., Li, H., Wang, J., Zhang, J., & Zhou, W. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3339661 · Cited by 116
“We leverage three types of data for vision language pre-training, including object labels on images [14], [15], [16] such as “man” or “backpack”, region annotations on images [16], [17] such as “boy wearing back-pack”, and text descriptions for images such as “The first day of school gives a mixed…”
MethodSelf-citationFar3D: Expanding the Horizon for Surround-View 3D Object Detection
Jiang, X., Li, S., Liu, Y., Wang, S., Jia, F., Wang, T., Han, L., & Zhang, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i3.28033 · Cited by 78
Self-citationMulti-Task Self-Training for Learning General Representations
Ghiasi, G., Zoph, B., Cubuk, E. D., Le, Q. V., & Lin, T.-Y. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00873 · Cited by 84
“showed similar findings using the Objects365 dataset [49].”
BackgroundResultInfluentialLearning to Generate Scene Graph from Natural Language Supervision
Zhong, Y., Shi, J., Yang, J., Xu, C., & Li, Y. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00184 · Cited by 73
“We additionally consider another object detector trained on Object365 dataset [39].”
MethodV*: Guided Visual Search as a Core Mechanism in Multimodal LLMs
Wu, P., & Xie, S. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01243 · Cited by 74
“Objects365 v2 [42] and GoldG [17] datasets are only used as detection data.”
MethodWu, Z., Liu, C., Wen, J., Xu, Y. D., Yang, J. J., & Li, X. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3231744 · Cited by 76
“However, its training requires the large-scale dataset with bounding-box annotations [13], [14], [15], which are labor-intensive and time-consuming to be collected.”
BackgroundCompressing Visual-linguistic Model via Knowledge Distillation
Fang, Z., Wang, J., Hu, X., Wang, L., Yang, Y., & Liu, Z. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00146 · Cited by 81
Tackling class imbalance in computer vision: a contemporary review
Saini, M., & Susan, S. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10557-6 · Cited by 79
Open-Vocabulary SAM: Segment and Recognize Twenty-Thousand Classes Interactively
Yuan, H., Li, X., Zhou, C., Li, Y., Chen, K., & Loy, C. C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72775-7_24 · Cited by 87
“In particular, we adopt more detection data (V3Det [57], Object365 [53]) and classification data (Im-ageNet22k [11]).”
MethodLarge-Scale Object Detection in the Wild From Imbalanced Multi-Labels
Peng, J., Bu, X., Sun, M., Zhang, Z., Tan, T., & Yan, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00973 · Cited by 67
“ges with 12.4 million boxes of 500 categories in its challenge split. The scale of training images is 15 times of the MS COCO [21] and 3 times of the second largest object detection dataset Object365 [30]. Considering the huge size of Open Images dataset, we split a mini Open Images dataset for our ablation study. The…”
BackgroundInfluentialVIVO: Visual Vocabulary Pre-Training for Novel Object Captioning
Hu, X., Yin, X. P., Lin, K., Zhang, L., Gao, J., Wang, L., & Liu, Z. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16249 · Cited by 77
“Thus, it opens the possibility of leveraging, for VLP, many existing vision datasets originally developed for image tagging or object detection tasks like ImageNet (Deng et al. 2009), Open Images (Kuznetsova et al. 2020), Objects365 (Shao et al. 2019), etc.”
BackgroundYOLOE: Real-time seeing anything
Wang, A., Liu, L., Chen, H., Lin, Z., Han, J., & Ding, G. (2025) · 2025 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02280 · Cited by 65
“Objects365 [52] Detection ✓ ✓ 609k 8,530k GQA [17] Grounding ✓ ✓ 621k 3,662k Flickr [43] Grounding ✓ ✓ 149k 638k Training.”
InfluentialT2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-Image Generation
Huang, K., Duan, C., Sun, K., Xie, E., Li, Z., & Liu, X. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3531907 · Cited by 195
“We employ the UniDet [78] model trained on 4 large-scale detection datasets (COCO [58], Objects365 [85], OpenImages [86], and Mapillary [87]).”
Self-citationDetGPT: Detect What You Need via Reasoning
Pi, R., Gao, J., Diao, S., Pan, R., Dong, H., Zhang, J., Yao, L., Han, J., Xu, H., Kong, L., et al. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.876 · Cited by 127
Self-citationBEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection
Li, Z., Lan, S., Álvarez, J. M., & Wu, Z. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01901 · Cited by 75
“ViT-L [10] is pretrained on COCO [33] and Objects365 [52], while ViT-Adapter-L [8] is pretrained on DINOv2 [47].”
BackgroundSelf-citation
Metadata
- Authors
- Shao, S., Li, Z., Zhang, T., Peng, C., Yu, G., Zhang, X., Li, J., & Sun, J.
- Affiliations
- Megvii (China) (CN)
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 8429-8438
- OpenAlex
- W2983943451
- Cited by
- 673
- References
- 42
- Citations by year
- 2026: 70 · 2025: 155 · 2024: 180 · 2023: 132 · 2022: 67 · 2021: 50 · 2020: 17 · 2019: 2
- FWCI
- 11.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- bounding box annotation, annotation pipeline, pre-trained models, representation learning, semantic segmentation, benchmark, COCO benchmark, CityPersons, ADE20K
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
