SPAM: Spatially Partitioned Attention Module in Deep Convolutional Neural Networks for Image Classification

Existing attention mechanisms often use fusion or compression to obtain the required information, but this leads to a large quantity of information lost in the spatial or channel dimension. In order to solve this problem, the Spatially Partitioned Attention Module (SPAM), a really effective and lightweight attention module that can help obtain attention without channel fusion or compression, was proposed in the paper. For the input intermediate feature map, the SPAM first adaptively used average pooling and maximum pooling features for feature extraction, replaced the point feature with the local block feature in space to reduce the amount of calculation and used the IN layer and depthwise convolution to capture global spatial attention. Meanwhile, the reconstruction of channel dimension information was directly completed by group convolu-lion. Finally, the interpolation operation was used to obtain overall attention and weight the input feature map. Notably, the SPAM can be easily embedded in various mainstream CNN architectures, and network performance can be significantly improved by increasing a few microparam-ctcrs and calculations. To demonstrate the effectiveness of the SPAM, numerous experiments were conducted on the ImageNet-lK, CIFAR-100, and Food-101 datasets, and the network's regions of interest were visualized using Grad-CAM. On the ImagcNct-lK, CIFAR-100, and Food-101 datasets, the SPAM improved the accuracy of the baseline network by up to about 1. 08%, 2. 46%, and 1. 09%, respectively. The results show that the performance of the network embedded with the SPAM components is greatly improved; compared to other commonly used lightweight attention mechanisms, the SPAM always works better; the SPAM can really induce the networks to pay more attention to the target object regions and accurately improve the expression ability of the networks. © 2023 Xi'an Jiaotong University. All rights reserved.