Squeeze-and-Attention Networks for Semantic Segmentation

By Zilong Zhong, Z. Q. Lin, Rene Bidart, Xiaodan Hu, Ibrahim Ben Daya, Jonathan Li, Alexander Wong. 2019

287 citations recorded by the source corpus.

The recent integration of attention mechanisms into segmentation networks improves their representational capabilities through a great emphasis on more informative features. However, these attention mechanisms ignore an implicit sub-task of semantic segmentation and are constrained by the grid structure of convolution kernels. In this paper, we propose a novel squeeze-and-attention network (SANet) architecture that leverages an effective squeeze-and-attention (SA) module to account for two distinctive characteristics of segmentation: i) pixel-group attention, and ii) pixel-wise prediction. Specifically, the proposed SA modules impose pixel-group attention on conventional convolution by introducing an 'attention' convolutional channel, thus taking into account spatial-channel inter-dependencies in an efficient manner. The final segmentation results are produced by merging outputs from four hierarchical stages of a SANet to integrate multi-scale contexts for obtaining an enhanced pixel-wise prediction. Empirical experiments on two challenging public datasets validate the effectiveness of the proposed SANets, which achieves 83.2 % mIoU (without COCO pre-training) on PASCAL VOC and a state-of-the-art mIoU of 54.4 % on PASCAL Context.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Dynamic Neural Networks: A Survey (2021, neutral): “Sa & Sp Image segmentation [34], [129], [146], [148], [150], [154], [156], [216], [217], [218], [219], [220], Image-to-image translation [221], Object detection [110], [111], [147], [148], [164], Semantic image synthesis [222], [223], [224], Computer Image denoising [225], Fine-grained classificatio”
Online Ensemble Model Compression Using Knowledge Distillation (2020, background): “These include Image Classification [24,17,20,40], Object Detection [31,3,26,30,12], Semantic Segmentation [16,4,44,5,45] among others.”
Dynamic Region-Aware Convolution (2020, background): “In semantic segmentation, [36] imposes a pixel-group attention to remedy the deficiency of spatial information in SENet and [15] builds a link between each pixel and its surrounding pixels to capture important information.”
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks (2021, unknown): “PSPNet [52] ResNet-101 82.6 DFN [53] ResNet-101 82.7 EncNet [54] ResNet-101 82.9 SANet [55] ResNet-101 83.2 DANet [4] ResNet-101 82.6 CFNet [56] ResNet-101 84.2 SpyGR [57] ResNet-101 84.2 EANet (Ours) ResNet-101 84.0”
AAU-Net: An Adaptive Attention U-Net for Breast Lesions Segmentation in Ultrasound Images (2022, background): “4) Comparison With Different Attention-Based Methods: In recent years, many attention-based methods have been proposed to improve the performance of networks, such as AGNet [40], SANet [41], ECA-Net [42], scSENet [43], SENet [44].”
Channel Expansion Convolutional Network for Image Classification (2020, background): “SANet [39] aggregates outputs from multiple layers’ Squeeze-and-Attention heads to generate a multi-scale category mask, thus solving the pixel grouping task that is often overlooked in semantic segmentation.”