Attention-Guided Second-Order Pooling Convolutional Networks
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2230-2234
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.Keywords
Funding Information
- National Natural Science Foundation of China
- Natural Science Foundation of Liaoning Province
This publication has 18 references indexed in Scilit:
- Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition2018
- Squeeze-and-Excitation Networks2018
- Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization2018
- Non-local Neural Networks2018
- SORT: Second-Order Response Transform for Visual Recognition2017
- Bilinear Convolutional Neural Networks for Fine-Grained Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deep Residual Learning for Image Recognition2016
- Multi-scale Orderless Pooling of Deep Convolutional Activation Features2014
- Factorization Machines2010
- ImageNet: A large-scale hierarchical image database2009