CVAIFeb 8, 2022

Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation

arXiv:2202.03680v1133 citationsHas Code
Originality Incremental advance
AI Analysis

This addresses the challenge of improving knowledge distillation for model compression in vision tasks, though it appears incremental as it builds on existing distillation frameworks.

The paper tackles the problem of knowledge distillation by proposing a method that retains inter-channel correlation to preserve feature diversity and homology, achieving state-of-the-art results including boosting ResNet18 beyond 72% Top-1 accuracy on ImageNet classification.

Knowledge Distillation has shown very promising abil-ity in transferring learned representation from the largermodel (teacher) to the smaller one (student).Despitemany efforts, prior methods ignore the important role ofretaining inter-channel correlation of features, leading tothe lack of capturing intrinsic distribution of the featurespace and sufficient diversity properties of features in theteacher network.To solve the issue, we propose thenovel Inter-Channel Correlation for Knowledge Distillation(ICKD), with which the diversity and homology of the fea-ture space of the student network can align with that ofthe teacher network. The correlation between these twochannels is interpreted as diversity if they are irrelevantto each other, otherwise homology. Then the student isrequired to mimic the correlation within its own embed-ding space. In addition, we introduce the grid-level inter-channel correlation, making it capable of dense predictiontasks. Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation,demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation. Toour knowledge, we are the first method based on knowl-edge distillation boosts ResNet18 beyond 72% Top-1 ac-curacy on ImageNet classification. Code is available at:https://github.com/ADLab-AutoDrive/ICKD.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes