Multiscale Progressive Complementary Fusion Network for Fine-Grained Visual Classification

In fine-grained visual classification(FGVC), small inter-class variations and large intra-class variations are always inherent attributes, so it is much more challenging than traditional classification tasks. Recent studies have mainly tackled this problem by employing attention mechanisms to locate the most discriminative parts. However, these methods tend to neglect other inconspicuous but distinguishable parts, and can not effectively fuse the features information of different scales and different degrees of discrimination. In this paper, we propose a multi-scale progressive complementary fusion network (MPCF-Net) to address these problems. In particular, we propose the following: (i) A three-step multi-scale progressive training method, which employs an image slicer to generate puzzle images at different scales followed by multi-step progressive training. This enables the network to capture multi-granularity local feature information and gradually expand its attention to global structural information as the training progresses for multi-granularity information fusion. (ii) A plug-and-play feature complementary enhancement module (FCEM) that explicitly enhances the features extracted by the current layer of the network, while also enabling the next layer of the network to extract potential complementary feature information to diversify the features. Our experiments were conducted on four FGVC benchmark datasets and yielded state-of-the-art and competitive results.