DECORE: Deep Compression With Reinforcement Learning

Manoj Alwani, Yang Wang, Vashisht Madhavan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 12349-12359

Abstract


Deep learning has become an increasingly popular and powerful methodology for modern pattern recognition systems. However, many deep neural networks have millions or billions of parameters, making them untenable for real-world applications due to constraints on memory size or latency requirements. As a result, efficient network compression techniques are often required for a widespread adoption of deep learning methods. We present DECORE, a reinforcement learning based approach to automate the network compression process. DECORE assigns an agent to each channel in the network along with a light policy gradient method to learn which neurons or channels to be kept or removed. Each agent in the network has just one parameter (keep or drop) to learn, which leads to a much faster training process compared to existing approaches. DECORE also gives state-of-the-art compression results on various network architectures and various datasets. For example, on the ResNet-110 architecture, DECORE achieves a 64.8% compression rate and 61.8% FLOPs reduction as compared to the baseline model without any major accuracy loss on the CIFAR-10 dataset. It can reduce the size of regular architectures like the VGG network by up to 99% with just a small accuracy drop of 2.28%. For a larger dataset like ImageNet it can compress the ResNet-50 architecture by 44.7% and reduces FLOPs by 42.3%, with just a 0.69% drop on Top-5 accuracy of the uncompressed model. We also demonstrate that DECORE can be used to search for compressed network architectures based on various constraints, such as memory and FLOPs.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Alwani_2022_CVPR, author = {Alwani, Manoj and Wang, Yang and Madhavan, Vashisht}, title = {DECORE: Deep Compression With Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {12349-12359} }