DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection
Open accessThe DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
Abstract
Knowledge distillation (KD) has recently gained great success in the field of object detection. By transferring the knowledge of the spatial or channel domain from the teacher model to the student model, it allows for a more compact representation with minimal performance loss. Despite this progress, existing KD methods typically treat knowledge from spatial or channel domains independently, ignoring the exploitation of the mutual relationship between these domains. In this work, we first explore the connection between spatial and channel domains and find there exists a strong correlation between them, i.e. the salient channels tend to contain significant object regions in the spatial domain. Motivated by this observation, we propose DCSF-KD, a novel Dynamic Channel-wise Spatial Feature Knowledge Distillation framework for object detection by fully exploiting both spatial and channel knowledge. Specifically, we introduce channel-wise spatial feature distillation and global channel attention distillation, using information from both domains to improve the accuracy of the student network. Experiments demonstrate that our DCSF-KD outperforms existing detection methods on both homogeneous and heterogeneous teacher-student network pairs. For example, when using the MaskRCNN-Swin detector as the teacher, and based on RetinaNet and FCOS with ResNet-50 on MS COCO, our DCSF-KD can achieve 41.9% and 44.1% mAP, respectively.
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
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
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
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
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
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Research works printed but not linked: 5
- Chen, G.; Choi, W.; Yu, X.; Han, T.; and Chandraker, M. 2017. Learning efficient object detection models with knowledge distillation. Advances in neural information pro- cessing systems, 30.
- Li, X.; Wang, W.; Wu, L.; Chen, S.; Hu, X.; Li, J.; Tang, J.; and Yang, J. 2020b. Generalized focal loss: Learning qual- ified and distributed bounding boxes for dense object detec- tion. Advances in Neural Information Processing Systems, 33: 21002-21012.
- Wang, Y.; Huang, W.; Sun, F.; Xu, T.; Rong, Y.; and Huang, J. 2020. Deep multimodal fusion by channel exchang- ing. Advances in neural information processing systems, 33: 4835-4845.
- Zhang, L.; and Ma, K. 2020. Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors. In International Conference on Learning Representations.
- Zhixing, D.; Zhang, R.; Chang, M.; Liu, S.; Chen, T.; Chen, Y.; et al. 2021. Distilling object detectors with feature rich- ness. Advances in Neural Information Processing Systems, 34: 5213-5224.
Cited by
Song, Y., Zhao, B., Wu, Y., Bai, X., & Zhang, B. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3622546 · Cited by 8
Knowledge distillation with spatial semantic enhancement for remote sensing object detection
Hu, K., Li, J., Ji, N., Xiang, X., Jiang, K., & Gao, X. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.01.017 · Cited by 5
Localized Background-Aware Generative Distillation for Enhanced Remote Sensing Object Detection
Wang, C., Sun, Y., Yang, J. J., & Luo, L. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3661231 · Cited by 4
Yi, J., Mao, J., Wang, Y., Liu, T., Li, M., Zeng, K., Zhang, H., & Chang, X. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3672967 · Cited by 4
SATE: Efficient knowledge distillation with implicit student-aware teacher ensembles
Chen, D., Li, Y., Liu, J., Zhou, J. W., & Gao, Y. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112355 · Cited by 3
Li, X., Di, X., Liu, M., & Ye, S. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104519 · Cited by 3
Sheng, L., Guo, Y., Long, J., Liu, Z., Ma, Q., Zhou, Z., & Dai, W. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02298-0 · Cited by 1
Dynamic Riemannian Geometry Relational Distillation for Lightweight 3-D Object Detection
Bu, C., Yan, W., Liu, Z., Song, Y., & Tang, C. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3703756 · Cited by 1
Direction Sensitivity–Based Knowledge Distillation: Optimization-Aware Low-Rank Knowledge Transfer
Liao, Y., Chen, X., Fu, Z., Wang, H., & Huang, J. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i28.39520
BiKD: Bidomain Knowledge Distillation for SAR Object Detection
Wang, X., Xu, W., Li, G., Lin, K. H., Xu, Z., & Wu, Y. (2026) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2026.3676449
On learning denoisable student logits
Chen, D., Li, Y., Liu, J., Kusý, B., Zhou, J. W., & Gao, Y. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113684
Dual feature masking stage-wise knowledge distillation for object detection
Zhang, Z., Li, J., Wu, Z., Shen, J., & Xu, J. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114955
Luo, G., Shi, Z., & Xie, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.17591
Fang, H., Huang, R., Chen, Q. Y., Wang, X., Chang, Y., & Yan, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37135-5_9
Dual-Domain Imitation with Normalization: Enhancing Feature Distillation for Object Detection
Zhang, M., Cheng, Z., Wang, J., He, X., He, T., & Lu, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3504-9_27
Self-citationCai, J., Su, X., Deng, H., & Deng, J. (2026) · Sensors · doi:10.3390/s26144599
Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition
Li, P., Ping, C., Song, J., & Song, M. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3836050
Making Knowledge Distillation Open Again
Yi, J., Lin, S., Zhang, H., Mao, J., Li, M., Gu, H., Li, Z., Zheng, Y., Chang, X., & Wang, Y. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3721359
Premavathi, T., Palaniappan, D., Gulzar, Y., & Ya’u, B. I. (2026) · IET Image Processing · doi:10.1049/ipr2.70461
Verma, A. K., Gandhudi, M., Khandelwal, M., Misra, R., & Singh, T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7398379
Li, J., Liu, Z., Bao, X., & Qu, M. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.116299
Domain-Aware Feature Distillation for Cross-Domain Object Detection
Wang, R., Xu, Y., Wei, Z., & Wu, Z. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835876
P2AD: Pose-Aware Pruning and Adaptive Distillation for Lightweight Human Pose Estimation
Lin, H., Guo, S., Cai, Z., Zhang, S., & Ye, L. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-7204-4_47
Metadata
- Authors
- Dai, T., Lin, Y., Guo, H., Wang, J., & Zhu, Z.
- Affiliations
- Shenzhen University (CN)
- Tsinghua University (CN)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2025-04-11
- Volume
- 39
- Issue
- 3
- Pages
- 2627-2635
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W4409369893
- Semantic Scholar
- 1d3f8fb85ce2b74a562d830e092f18b93bfa2f3a
- Cited by
- 23
- References
- 36
- Citations by year
- 2026: 20 · 2025: 3
- FWCI
- 4.61
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- Funders
- National Natural Science Foundation of China (62471310)
- 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
- knowledge distillation, object detection, channel attention, teacher-student models, model compression, Mask R-CNN, RetinaNet, FCOS
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.