GRAD-CAM Guided Channel-Spatial Attention Module for Fine-Grained Visual Classification

Fine-grained visual classification (FGVC) is becoming an important research field, due to its wide applications and the rapid development of computer vision technologies. The current state-of-the-art (SOTA) methods in the FGVC usually employ attention mechanisms to first capture the semantic parts and then discover their subtle differences between distinct classes. The existing attention modules have significantly improved the classification performance but they are poorly guided since part-based detectors in the FGVC depend on the network learning ability without the supervision of part annotations. As obtaining such part annotations is labor-expensive, some visual localization and explanation methods, such as gradient-weighted class activation mapping (Grad-CAM), can be utilized for supervising the attention mechanism. In this paper, we propose a Grad-CAM guided channel-spatial attention module for the FGVC, which employs the Grad-CAM to supervise and constrain the attention weights by generating the coarse localization maps. To demonstrate the effectiveness of the proposed method, we conduct comprehensive experiments on three popular FGVC datasets, including CUB-200-2011, Stanford Cars, and FGVC-Aircraft datasets. The proposed method outperforms the SOTA attention modules in the FGVC task. In addition, visualizations of the feature maps demonstrate the superiority of the proposed method against the SOTA approaches.