Distilling Object Detectors via Decoupled Features
Open accessThe DOI matches its Crossref record; 65 of the 65 references it cites were found in a registry or an index.
Abstract
Knowledge distillation is a widely used paradigm for inheriting information from a complicated teacher network to a compact student network and maintaining the strong performance. Different from image classification, object detectors are much more sophisticated with multiple loss functions in which features that semantic information rely on are tangled. In this paper, we point out that the information of features derived from regions excluding objects are also essential for distilling the student detector, which is usually ignored in existing approaches. In addition, we elucidate that features from different regions should be assigned with different importance during distillation. To this end, we present a novel distillation algorithm via decoupled features (DeFeat) for learning a better student detector. Specifically, two levels of decoupled features will be processed for embedding useful information into the student, i.e., decoupled features from neck and decoupled proposals from classification head. Extensive experiments on various detectors with different backbones show that the proposed DeFeat is able to surpass the state-of-the-art distillation methods for object detection. For example, DeFeat improves ResNet50 based Faster R-CNN from 37.4% to 40.9% mAP, and improves ResNet50 based RetinaNet from 36.5% to 39.7% mAP on COCO benchmark. Code will be released1,2.
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
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
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 · cited 4×
“02 for FPN [33] and RetinaNet [34], respectively.”
BackgroundMethodInfluentialHe, 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
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · cited 6×
“The input image is resized such that its shorter side has 800 pixels on COCO and 600 pixels on VOC.”
MethodResultInfluential
Research works printed but not linked: 6
- kim, 2018, Paraphrasing complex network: Network compression via factor transfer, Advances in neural information processing systems, 2760
- han, 2015, Learning both weights and connections for efficient neural network, Advances in neural information processing systems, 1135
- wang, 2018, Pelee: A real-time object detection system on mobile devices, Advances in neural information processing systems, 1963
- guo, 2016, Dynamic network surgery for efficient dnns, Advances in neural information processing systems, 1379
- chen, 2017, Learning efficient object detection models with knowledge distillation, Advances in neural information processing systems, 742
- 10.1109/CVPR42600.2020.01079 · doi:10.1109/cvpr42600.2020.01079 · Paper page
Cited by
A review of convolutional neural network architectures and their optimizations
Cong, S., & Zhou, Y. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10213-5 · Cited by 381
Focal and Global Knowledge Distillation for Detectors
Yang, Z., Li, Z., Jiang, X., Gong, Y., Yuan, Z., Zhao, D., & Yuan, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00460 · Cited by 380
Masked Generative Distillation
Yang, Z., Li, Z., Shao, M., Shi, D., Yuan, Z., & Yuan, C. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20083-0_4 · Cited by 269
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
“DeFeat [16] leverages different loss weights when conducting feature imitation on the object regions and the background region.”
BackgroundMethodInfluentialOvercoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
Feng, T., Wang, M., & Yuan, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00921 · Cited by 132
DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection
Dai, T., Lin, Y., Guo, H., Wang, J., & Zhu, Z. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i3.32266 · Cited by 23
Metadata
- Authors
- Guo, J., Han, K., Wang, Y., Wu, H., Chen, X., Xu, C., & Xu, C.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 2154-2164
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3176459575
- Cited by
- 266
- References
- 65
- FWCI
- 15.85
- Type
- conference paper
- Language
- en
- Open access
- green
- Funders
- Australian Research Council
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.