Journal
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Volume -, Issue -, Pages 1455-1464Publisher
IEEE
DOI: 10.1109/CVPR42600.2020.00153
Keywords
-
Categories
Funding
- National Natural Science Foundation of China [61772256, 61921006]
Ask authors/readers for more resources
Filter level pruning is an effective method to accelerate the inference speed of deep CNN models. Although numerous pruning algorithms have been proposed, there are still two open issues. The first problem is how to prune residual connections. We propose to prune both channels inside and outside the residual connections via a KL-divergence based criterion. The second issue is pruning with limited data. We observe an interesting phenomenon: directly pruning on a small dataset is usually worse than fine-tuning a small model which is pruned or trained from scratch on the large dataset. Knowledge distillation is an effective approach to compensate for the weakness of limited data. However, the logits of a teacher model may be noisy. In order to avoid the influence of label noise, we propose a label refinement approach to solve this problem. Experiments have demonstrated the effectiveness of our method (CURL, Compression Using Residual-connections and Limited-data). CURL significantly outperforms previous state-of-the-art methods on ImageNet. More importantly, when pruning on small datasets, CURL achieves comparable or much better performance than fine-tuning a pretrained small model.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available