Abstract
We present a filter correlation based model compression approach for deep convolutional neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise correlations and drops one of the filters from each such pair. However, instead of discarding one of the filters from each such pair naïvely, the model is re-optimized to make the filters in these pairs maximally correlated, so that discarding one of the filters from the pair results in minimal information loss. Moreover, after discarding the filters in each round, we further finetune the model to recover from the potential small loss incurred by the compression. We evaluate our proposed approach using a comprehensive set of experiments and ablation studies. Our compression method yields state-of-the-art FLOPs compression rates on various benchmarks, such as LeNet-5, VGG-16, and ResNet-50, 56, while still achieving excellent predictive performance for tasks such as object detection on benchmark datasets.
Original language | English |
---|---|
Title of host publication | Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020 |
Publisher | IEEE |
Pages | 824-833 |
Number of pages | 10 |
ISBN (Electronic) | 9781728165530 |
DOIs | |
Publication status | Published - 14 May 2020 |
Event | 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 - Snowmass Village, USA United States Duration: 1 Mar 2020 → 5 Mar 2020 |
Publication series
Name | Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020 |
---|
Conference
Conference | 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 |
---|---|
Country/Territory | USA United States |
City | Snowmass Village |
Period | 1/03/20 → 5/03/20 |
Funding
PS is supported by the Research-I Foundation at IIT Kanpur. VKV acknowledges support from Visvesvaraya PhD Fellowship and PR acknowledges support from Visvesvaraya Young Faculty Fellowship.
ASJC Scopus subject areas
- Computer Science Applications
- Computer Vision and Pattern Recognition