journal article

Journal Article

New Generation Computing. 2024, 42(4), p. 825-843

MANet: Mixed Attention Network for Visual Explanation

Springer

English

2024-05-23

https://doi.org/10.1007/s00354-024-00252-7

The version of record of this article, first published in New Generation Computing, is available online at Publisher’s website: https://doi.org/10.1007/s00354-024-00252-7.

Various visual explanation methods, such as CAM and Grad-CAM, have been proposed to visualize and interpret predictions made by CNNs. Recent efforts go beyond mere visual interpretability, aiming to enhance CNN performance through the utilization of these generated visual explanations. In this work, we propose MANet (Mixed Attention Network)—a network architecture that advances the stability of visual explanations through an adaptive feature refinement mechanism via a mixed attention module. Concurrently, the generated attention maps are harnessed to bolster network performance in image recognition tasks. Experimental findings underscore the efficacy of MANet, demonstrating improved visual stability and consistency. The proposed architecture not only surpasses baseline models in image classification and object detection tasks but also establishes a novel paradigm for synergizing visual interpretability and network performance enhancement.

This article is licensed under a Creative Commons Attribution 4.0 International License.

96468

MANet: Mixed Attention Network for Visual Explanation

Springer

English

2024-05-23

New Generation Computing

42

4

825

843

https://doi.org/10.1007/s00354-024-00252-7

https://hdl.handle.net/11094/96468