Disentangle Your Dense Object Detector
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. In this paper, we investigate three such important conjunctions: 1) only samples assigned as positive in classification head are used to train the regression head; 2) classification and regression share the same input feature and computational fields defined by the parallel head architecture; and 3) samples distributed in different feature pyramid layers are treated equally when computing the loss. We first carry out a series of pilot experiments to show disentangling such conjunctions can lead to persistent performance improvement. Then, based on these findings, we propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art dense object detectors. Extensive experiments on MS COCO benchmark show that our approach can lead to 2.0~mAP, 2.4~mAP and 2.2~mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead. Notably, our best model reaches 55.0 mAP on the COCOtest-dev set and 93.5 AP on the hard subset of WIDER FACE, achieving new state-of-the-art performance on these two competitive benchmarks. Code is available at https://github.com/zehuichen123/DDOD.
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
ImageNet: 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
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
Deformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · cited 5×
“In order to get better performance on WIDER FACE, which is different from COCO, we adopt DCN [6], SSH module [27], and DIoU loss [58] on original ATSS model, reaching an overall AP of 93.0.”
InfluentialCascade R-CNN: Delving Into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00644 · Cited by 7,370
FCOS: Fully Convolutional One-Stage Object Detection
Tian, Z., Shen, C., Chen, H., & He, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00972 · Cited by 7,013
Stacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634 · cited 1×
“ResNet [13]; X: ResNeXt [44]; HG: Hourglass [29]; DCN: Deformable Convolutional Network [6]; and R2: Res2Net [11].”
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2019) · arXiv · doi:10.48550/arxiv.1911.08287 · Cited by 5,313 · cited 1×
“In order to get better performance on WIDER FACE, which is different from COCO, we adopt DCN [6], SSH module [28], and DIoU loss [55], reaching an overall AP of 93.”
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6999 · Cited by 5,288
Cited by
Road Scene Multi-Object Detection Algorithm Based on CMS-YOLO
Lv, Z., Wang, R., Wang, Y., Zhou, F., & Guo, N. (2023) · IEEE Access · doi:10.1109/access.2023.3327735 · Cited by 17
Metadata
- Authors
- Chen, Z., Yang, C., Li, Q., Zhao, F., Zha, Z.-J., & Wu, F.
- Venue
- Proceedings of the 29th ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2021-10-17
- Pages
- 4939-4948
- OpenAlex
- W3205483686
- Cited by
- 192
- References
- 17
- FWCI
- 9.53
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Disentangle Your Dense Object Detector. https://app.cochat.ai/papers/10.1145/3474085.3475351
- The paper
- Chen, Z., Yang, C., Li, Q., Zhao, F., Zha, Z.-J., & Wu, F. (2021). Disentangle Your Dense Object Detector. Proceedings of the 29th ACM International Conference on Multimedia. https://doi.org/10.1145/3474085.3475351
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.