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.

中文翻译：

---

REPrune：通过代表选举进行过滤修剪

尽管基于范数的过滤器修剪方法被广泛接受，但在确定要修剪的过滤器时，“较小范数不重要”的标准是否是最佳的还是值得怀疑的。特别是当我们只能保留原始过滤器的一小部分时，更重要的是选择最能代表整个过滤器的过滤器，而不管范数如何。我们名为“REPrune”的新型修剪方法通过聚类选择具有代表性的过滤器来解决这个问题。通过从一组相似的过滤器中选择一个过滤器并避免选择相邻的大过滤器，REPrune 可以在相似的精度下获得更好的压缩率。我们的方法还可以更快地恢复精度，并且在微调期间需要较小的滤波器移位。根据经验，REPrune 减少了超过 49% 的 FLOP，为 0。CIFAR-10 在 ResNet-110 上的准确度提高了 53%。此外，REPrune 在 ImageNet 的 ResNet-18 上减少了 41.8% 以上的 FLOP，Top-1 验证损失为 1.67%。