Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.48550/arxiv.2207.01580
Abstract: In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the… read more here.
Keywords: asymmetric computation; dynamic spatial; spatial sparsification; vision transformers ... See more keywords