2020/07/14 by Min-Cheol Park, Mincheol Park, Park, Mincheol +4 · 4 citations
Computer Science · #Artificial intelligence #Biology #Business #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #FOS: Computer and information sciences #Filter (signal processing) #Horticulture #Imbalanced Data Classification Techniques #Internet Traffic Analysis and Secure E-voting #Network Security and Intrusion Detection #Pruning #cs.CV
paper · pdf · doi:10.48550/arxiv.2007.06932
published in arXiv (Cornell University) (Cornell University) · Under Review at ECCV 2020
openalex publication_date 2020/07/14 · arxiv created 2020/07/21 · arxiv updated 2020/07/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Even though norm-based filter pruning methods are widely accepted, it is questionable whether the "smaller-norm-less-important" criterion is optimal in determining filters to prune. Especially when we can keep only a small fraction of the original filters, it is more crucial to choose the filters that can best represent the whole filters regardless of norm values. Our novel pruning method entitled "REPrune" addresses this problem by selecting representative filters via clustering. By selecting one filter from a cluster of similar filters and avoiding selecting adjacent large filters, REPrune can achieve a better compression rate with similar accuracy. Our method also recovers the accuracy more rapidly and requires a smaller shift of filters during fine-tuning. Empirically, REPrune reduces more than 49% FLOPs, with 0.53% accuracy gain on ResNet-110 for CIFAR-10. Also, REPrune reduces more than 41.8% FLOPs with 1.67% Top-1 validation loss on ResNet-18 for ImageNet.