Salient Mask-Guided Vision Transformer for Fine-Grained Classification
This addresses the challenge of focusing on truly discriminative regions in fine-grained classification for computer vision applications, representing an incremental improvement over existing ViT-based methods.
The paper tackled the problem of fine-grained visual classification by boosting Vision Transformer attention maps with salient masking of discriminative foreground regions, achieving state-of-the-art performance on benchmarks with fewer resources and lower input resolution.
Fine-grained visual classification (FGVC) is a challenging computer vision problem, where the task is to automatically recognise objects from subordinate categories. One of its main difficulties is capturing the most discriminative inter-class variances among visually similar classes. Recently, methods with Vision Transformer (ViT) have demonstrated noticeable achievements in FGVC, generally by employing the self-attention mechanism with additional resource-consuming techniques to distinguish potentially discriminative regions while disregarding the rest. However, such approaches may struggle to effectively focus on truly discriminative regions due to only relying on the inherent self-attention mechanism, resulting in the classification token likely aggregating global information from less-important background patches. Moreover, due to the immense lack of the datapoints, classifiers may fail to find the most helpful inter-class distinguishing features, since other unrelated but distinctive background regions may be falsely recognised as being valuable. To this end, we introduce a simple yet effective Salient Mask-Guided Vision Transformer (SM-ViT), where the discriminability of the standard ViT`s attention maps is boosted through salient masking of potentially discriminative foreground regions. Extensive experiments demonstrate that with the standard training procedure our SM-ViT achieves state-of-the-art performance on popular FGVC benchmarks among existing ViT-based approaches while requiring fewer resources and lower input image resolution.