The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
VarifocalNet: An IoU-aware Dense Object Detector
Open accessAbstract
Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates. However, neither option results in a reliable ranking, thus degrading detection performance. In this paper, we propose to learn an Iou-Aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy. We show that dense object detectors can achieve a more accurate ranking of candidate detections based on the IACS. We design a new loss function, named Varifocal Loss, to train a dense object detector to predict the IACS, and propose a new star-shaped bounding box feature representation for IACS prediction and bounding box refinement. Combining these two new components and a bounding box refinement branch, we build an IoU-aware dense object detector based on the FCOS+ATSS architecture, that we call VarifocalNet or VFNet for short. Extensive experiments on MS COCO show that our VFNet consistently surpasses the strong baseline by ~2.0 AP with different backbones. Our best model VFNet-X-1200 with Res2Net-101-DCN achieves a single-model single-scale AP of 55.1 on COCO test-dev, which is state-of-the-art among various object detectors. Code is available at: https://github.com/hyz-xmaster/VarifocalNet.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
Faster 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
Faster 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
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
(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
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Research works printed but not linked: 1
- 10.1109/CVPR42600.2020.01079 · doi:10.1109/cvpr42600.2020.01079 · Paper page
Cited by
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00721 · Cited by 13,198
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022) · arXiv · doi:10.48550/arxiv.2207.02696 · Cited by 13,205
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5040083 · Cited by 3,052
Zhu, X., Lyu, S., Wang, X., & Zhao, Q. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00312 · Cited by 2,208
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.02976 · Cited by 1,792
“We choose VFL as the classification loss function.”
BackgroundMethodInfluentialTOOD: Task-aligned One-stage Object Detection
Feng, C., Zhong, Y., Gao, Y., Scott, M. R., & Huang, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00349 · Cited by 1,668
“0 VFNet [29]† CVPR21 ResNeXt-101-64×4d-DCN 49.”
Hussain, M. (2023) · Machines · doi:10.3390/machines11070677 · Cited by 1,217
“Varifocal loss (VFL) [67] is used as the classi fi cation loss and distribution focal loss (DFL) , balancing locations boundaries are blurred.”
MethodInfluentialSlicing Aided Hyper Inference and Fine-Tuning for Small Object Detection
Akyon, F. C., Onur Altinuc, S., & Temizel, A. (2022) · 2022 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip46576.2022.9897990 · Cited by 572
YOLO-based Object Detection Models: A Review and its Applications
Vijayakumar, A., & Vairavasundaram, S. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18872-y · Cited by 470
A review on deep learning in UAV remote sensing
Osco, L. P., Marcato Junior, J., Marques Ramos, A. P., de Castro Jorge, L. A., Fatholahi, S. N., de Andrade Silva, J., Matsubara, E. T., Pistori, H., Gonçalves, W. N., & Li, J. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102456 · Cited by 458
Li, X., Wang, W., Hu, X., Li, J., Tang, J., & Yang, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01146 · Cited by 450
RDD-YOLO: A modified YOLO for detection of steel surface defects
Zhao, C., Shu, X., Yan, X., Zuo, X., & Zhu, F. (2023) · Measurement · doi:10.1016/j.measurement.2023.112776 · Cited by 386
MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface
Guo, Z., Wang, C., Yang, G., Huang, Z., & Li, G. (2022) · Sensors · doi:10.3390/s22093467 · Cited by 313
Boosting R-CNN: Reweighting R-CNN samples by RPN’s error for underwater object detection
Song, P., Li, P., Dai, L., Wang, T., & Chen, Z. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.01.088 · Cited by 298
DEIM: DETR with Improved Matching for Fast Convergence
Huang, S., Lu, Z., Cun, X., Yu, Y., Zhou, X., & Shen, X. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.01412 · Cited by 296
RangeDet: In Defense of Range View for LiDAR-based 3D Object Detection
Fan, L., Xiong, X., Wang, F., Wang, N., & Zhang, Z. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00291 · Cited by 257
Localization Distillation for Dense Object Detection
Zheng, Z., Ye, R., Wang, P., Ren, D., Zuo, W., Hou, Q., & Cheng, M.-M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00919 · Cited by 220
Li, Z., Zhang, Y., Wu, H., Suzuki, S., Namiki, A., & Wang, W. (2023) · Remote Sensing · doi:10.3390/rs15030865 · Cited by 160
PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices
Yu, G., Chang, Q., Lv, W., Xu, C., Cui, C., Ji, W., Dang, Q., Deng, K., Wang, G., Du, Y., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.00902 · Cited by 112
“Replacing QFL with VFL, the mAP (0.5:0.95) is improved to 29.2 from 29.1.”
MethodInfluentialEL-YOLO: An efficient and lightweight low-altitude aerial objects detector for onboard applications
Xue, C., Xia, Y., Wu, M., Chen, Z., Cheng, F., & Yun, L. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124848 · Cited by 82
Autonomous health assessment of civil infrastructure using deep learning and smart devices
Agyemang, I. O., Zhang, X., Acheampong, D., Adjei-Mensah, I., Kusi, G. A., Mawuli, B. C., & Agbley, B. L. Y. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104396 · Cited by 43
Bur, A. M., Zhang, T., Chen, X., Kavookjian, H., Kraft, S., Karadaghy, O., Farrokhian, N., Mussatto, C., Penn, J., & Wang, G. (2023) · Otolaryngology–Head and Neck Surgery · doi:10.1002/ohn.411 · Cited by 25
Real-Time Object Detection on Edge Devices: A Fisheye Specific DFINE
Park, J., Lee, J., & Yong, Y. (2025) · 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw69036.2025.00573 · Cited by 4
Metadata
- Authors
- Zhang, H., Wang, Y., Dayoub, F., & Sunderhauf, N.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 8510-8519
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3172087149
- Cited by
- 1,142
- References
- 57
- FWCI
- 61.51
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.