A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition
This work solves the challenge of recognizing subtle object differences in fine-grained visual recognition, which is important for applications like species identification, but it is incremental as it builds on existing ViT methods.
The paper tackled the problem of fine-grained visual recognition by addressing ViT's limitation in generating multi-granularity features due to fixed patch sizes, proposing AFTrans to adaptively capture region attention without box annotations, achieving state-of-the-art performance on benchmarks like CUB-200-2011, Stanford Dogs, and iNat2017.
Learning subtle representation about object parts plays a vital role in fine-grained visual recognition (FGVR) field. The vision transformer (ViT) achieves promising results on computer vision due to its attention mechanism. Nonetheless, with the fixed size of patches in ViT, the class token in deep layer focuses on the global receptive field and cannot generate multi-granularity features for FGVR. To capture region attention without box annotations and compensate for ViT shortcomings in FGVR, we propose a novel method named Adaptive attention multi-scale Fusion Transformer (AFTrans). The Selective Attention Collection Module (SACM) in our approach leverages attention weights in ViT and filters them adaptively to correspond with the relative importance of input patches. The multiple scales (global and local) pipeline is supervised by our weights sharing encoder and can be easily trained end-to-end. Comprehensive experiments demonstrate that AFTrans can achieve SOTA performance on three published fine-grained benchmarks: CUB-200-2011, Stanford Dogs and iNat2017.