SNF: Filter Pruning via Searching the Proper Number of Filters
This work addresses the challenge of efficiently deploying CNNs on resource-constrained devices by optimizing filter pruning, though it is incremental as it builds on existing pruning methods by focusing on layer-specific filter counts.
The paper tackles the problem of filter pruning in convolutional neural networks by proposing SNF, a method that searches for the optimal number of filters to retain per layer, achieving state-of-the-art accuracy on CIFAR-10 with a 0.14% increase in Top-1 accuracy at 52.94% FLOPs reduction and competitive performance on ImageNet with only a 0.74% drop in Top-1 accuracy at 52.10% FLOPs reduction.
Convolutional Neural Network (CNN) has an amount of parameter redundancy, filter pruning aims to remove the redundant filters and provides the possibility for the application of CNN on terminal devices. However, previous works pay more attention to designing evaluation criteria of filter importance and then prune less important filters with a fixed pruning rate or a fixed number to reduce convolutional neural networks' redundancy. It does not consider how many filters to reserve for each layer is the most reasonable choice. From this perspective, we propose a new filter pruning method by searching the proper number of filters (SNF). SNF is dedicated to searching for the most reasonable number of reserved filters for each layer and then pruning filters with specific criteria. It can tailor the most suitable network structure at different FLOPs. Filter pruning with our method leads to the state-of-the-art (SOTA) accuracy on CIFAR-10 and achieves competitive performance on ImageNet ILSVRC-2012.SNF based on the ResNet-56 network achieves an increase of 0.14% in Top-1 accuracy at 52.94% FLOPs reduction on CIFAR-10. Pruning ResNet-110 on CIFAR-10 also improves the Top-1 accuracy of 0.03% when reducing 68.68% FLOPs. For ImageNet, we set the pruning rates as 52.10% FLOPs, and the Top-1 accuracy only has a drop of 0.74%. The codes can be available at https://github.com/pk-l/SNF.