Exploring Inter-Channel Correlation for Diversity-preserved Knowledge Distillation
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of the IEEE International Conference on Computer Vision, 2021, 00, pp. 8251-8260
- Issue Date:
- 2021-01-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
KD_ICCV2021 (1).pdf | Submitted version | 6.36 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Knowledge Distillation has shown very promising ability in transferring learned representation from the larger model (teacher) to the smaller one (student). Despite many efforts, prior methods ignore the important role of retaining inter-channel correlation of features, leading to the lack of capturing intrinsic distribution of the feature space and sufficient diversity properties of features in the teacher network. To solve the issue, we propose the novel Inter-Channel Correlation for Knowledge Distillation (ICKD), with which the diversity and homology of the feature space of the student network can align with that of the teacher network. The correlation between these two channels is interpreted as diversity if they are irrelevant to each other, otherwise homology. Then the student is required to mimic the correlation within its own embedding space. In addition, we introduce the grid-level inter-channel correlation, making it capable of dense prediction tasks. Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation. To our knowledge, we are the first method based on knowledge distillation boosts ResNet18 beyond 72% Top-1 accuracy on ImageNet classification. Code is available at: https://github.com/ADLab-AutoDrive/ICKD.
Please use this identifier to cite or link to this item: