Abs-CAM: a gradient optimization interpretable approach for explanation of convolutional neural networks

• DOI: 10.1007/s11760-022-02313-0
• Publication Date: 2022-07-29T14:45:42Z
• Authors: Chunyan Zeng; Kang Yan; Zhifeng Wang; Yan Yu; Shiyan Xia; Nan Zhao
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Science - Artificial Intelligence; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 02 engineering and technology; Machine Learning (cs.LG); 03 medical and health sciences; Artificial Intelligence (cs.AI); 0302 clinical medicine; 0202 electrical engineering, electronic engineering, information engineering

Abs-CAM for Explanation of Convolutional Neural Networks<br/>The black-box nature of Deep Neural Networks (DNNs) severely hinders its performance improvement and application in specific scenes. In recent years, class activation mapping-based method has been widely used to interpret the internal decisions of models in computer vision tasks. However, when this method uses backpropagation to obtain gradients, it will cause noise in the saliency map, and even locate features that are irrelevant to decisions. In this paper, we propose an Absolute value Class Activation Mapping-based (Abs-CAM) method, which optimizes the gradients derived from the backpropagation and turns all of them into positive gradients to enhance the visual features of output neurons' activation, and improve the localization ability of the saliency map. The framework of Abs-CAM is divided into two phases: generating initial saliency map and generating final saliency map. The first phase improves the localization ability of the saliency map by optimizing the gradient, and the second phase linearly combines the initial saliency map with the original image to enhance the semantic information of the saliency map. We conduct qualitative and quantitative evaluation of the proposed method, including Deletion, Insertion, and Pointing Game. The experimental results show that the Abs-CAM can obviously eliminate the noise in the saliency map, and can better locate the features related to decisions, and is superior to the previous methods in recognition and localization tasks.<br/>