Author:
Joo Donggyu,Yi Eojindl,Baek Sunghyun,Kim Junmo
Abstract
Convolutional neural networks (CNNs) have achieved remarkable results; however, despite the development of deep learning, practical user applications are fairly limited because heavy networks can be used solely with the latest hardware and software supports. Therefore, network pruning is gaining attention for general applications in various fields. This paper proposes a novel channel pruning method, Linearly Replaceable Filter (LRF), which suggests that a filter that can be approximated by the linear combination of other filters is replaceable. Moreover, an additional method called Weights Compensation is proposed to support the LRF method. This is a technique that effectively reduces the output difference caused by removing filters via direct weight modification. Through various experiments, we have confirmed that our method achieves state-of-the-art performance in several benchmarks. In particular, on ImageNet, LRF-60 reduces approximately 56% of FLOPs on ResNet-50 without top-5 accuracy drop. Further, through extensive analyses, we proved the effectiveness of our approaches.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
13 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Weight-adaptive channel pruning for CNNs based on closeness-centrality modeling;Applied Intelligence;2023-12-07
2. Lottery Jackpots Exist in Pre-Trained Models;IEEE Transactions on Pattern Analysis and Machine Intelligence;2023-12
3. Reconstructing Pruned Filters using Cheap Spatial Transformations;2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW);2023-10-02
4. Performance-Aware Approximation of Global Channel Pruning for Multitask CNNs;IEEE Transactions on Pattern Analysis and Machine Intelligence;2023-08
5. WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04