Granularity-aware distillation and structure modeling region proposal network for fine-grained image classification

Xiao Ke, Yuhang Cai, Baitao Chen, Hao Liu, Wenzhong Guo

Abstract: Highlights•We propose a granularity-aware distillation module to enhance the representation ability of the model. We adopt a multi-granularity feature fusion learning strategy to jointly learn multi-level information, and use cross-layer self-distillation regularization to improve the robustness of features at different granularity levels.•We propose a structure modeling region proposal module. Based on the collaborative learning of discriminative semantics and structural semantics under weak supervision, the model can improve the ability to capture multi-granularity discriminative regions and mine regional structural semantic associations.•GDSMP-Net reports state-of-the-art performance on four widely-used challenging datasets, including CUB-200-2011, Stanford Cars, FGVC-Aircraft and NA-birds.