CoChat

DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection

Open access
Dai, Tao, Lin, Yang, Guo, Hang, Wang, Jinbao, Zhu, Zexuan · 2025 · Proceedings of the AAAI Conference on Artificial Intelligence

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1609/aaai.v39i3.32266

Cites

39 of 39 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 5

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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

See all 23

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
Cited by
23
References
36
Citations by year
2026: 20 · 2025: 3
FWCI
4.61
Type
conference paper
Language
en
Open access
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.