Improved Bilinear Pooling With Pseudo Square-Rooted Matrix
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2023.3262059
Abstract: Bilinear pooling is a feature aggregation step applied after the convolutional layers of a deep network and encodes a matrix of local features into a fixed-size bilinear representation. It improves performance in many image classification… read more here.
Keywords: bilinear pooling; square rooted; rooted matrix; normalization ... See more keywords