HRank

2000년 도입 · 논문 1편에서 사용

HRank is a filter pruning method that explores the High Rank of the feature map in each layer (HRank). The proposed HRank is inspired by the discovery that the average rank of multiple feature maps generated by a single filter is always the same, regardless of the number of image batches CNNs receive. Based on HRank, the authors develop a method that is mathematically formulated to prune filters with low-rank feature maps.

출처: HRank: Filter Pruning using High-Rank Feature Map

소개 논문: HRank: Filter Pruning using High-Rank Feature Map