Interpretable Attention Guided Network for Fine-grained Visual Classification
It addresses the lack of interpretability in deep neural networks for fine-grained classification, which is critical for distinguishing subtle intra-class variations, though it appears incremental as it builds on existing attention-based methods.
The paper tackles the problem of fine-grained visual classification by proposing an Interpretable Attention Guided Network (IAGN) that extracts discriminative regions in an interpretable way, achieving competitive performance on standard benchmark datasets.
Fine-grained visual classification (FGVC) is challenging but more critical than traditional classification tasks. It requires distinguishing different subcategories with the inherently subtle intra-class object variations. Previous works focus on enhancing the feature representation ability using multiple granularities and discriminative regions based on the attention strategy or bounding boxes. However, these methods highly rely on deep neural networks which lack interpretability. We propose an Interpretable Attention Guided Network (IAGN) for fine-grained visual classification. The contributions of our method include: i) an attention guided framework which can guide the network to extract discriminitive regions in an interpretable way; ii) a progressive training mechanism obtained to distill knowledge stage by stage to fuse features of various granularities; iii) the first interpretable FGVC method with a competitive performance on several standard FGVC benchmark datasets.