Attention-Guided Second-Order Pooling Convolutional Networks
Lists
Only you see this
Abstract
Recently, channel attention-guided convolutional networks (ConvNets) have shown great advance on visual recognition tasks. However, they mainly exploit coarse first-order statistics to characterize holistic image and rarely focus on long-range feature dependencies, which limits the representation power in a certain. To handle above limitations, this paper proposes a novel attention-guided second-order pooling convolutional network (ASP-Net). ASP-Net introduces bilinear pooling that captures pairwise feature interactions to model second-order statistics. Meanwhile, it explicitly collects long-range dependencies via non-local operations, thus providing a global view in lower layers. Then, the second-order statistics and non-local context features are fused to obtain the enhanced representation for predicting channel-wise attention map and scaling convolution features. Experiment results on three commonly used datasets illuminate that ASP-Net outperforms its counterparts and achieves competitive performance. The source code is available at https://github.com/ShannanChen/ASPNet.
BibTeX
@inproceedings{chen2021attention,
author = {Shannan Chen and Qiule Sun and Cunhua Li and Jianxin Zhang and Qiang Zhang},
title = {{Attention-Guided Second-Order Pooling Convolutional Networks}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2021},
url = {https://openreview.net/forum?id=ClTOHLAqYO},
}Loading related content...