Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches

TL;DR

This paper introduces a novel progressive training framework for fine-grained visual classification that effectively fuses multi-granularity features using a jigsaw patch generator, achieving state-of-the-art results.

Contribution

It proposes a new progressive multi-granularity training method with a jigsaw patch generator for better feature learning in FGVC.

Findings

Achieves state-of-the-art performance on FGVC benchmarks.

Effectively fuses multi-granularity features for improved classification.

Outperforms or matches existing methods on standard datasets.

Abstract

Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works mainly tackle this problem by focusing on how to locate the most discriminative parts, more complementary parts, and parts of various granularities. However, less effort has been placed to which granularities are the most discriminative and how to fuse information cross multi-granularity. In this work, we propose a novel framework for fine-grained visual classification to tackle these problems. In particular, we propose: (i) a progressive training strategy that effectively fuses features from different granularities, and (ii) a random jigsaw patch generator that encourages the network to learn features at specific granularities. We obtain state-of-the-art performances on several standard FGVC benchmark datasets, where the proposed method consistently outperforms existing methods or delivers competitive results. The code will be available at https://github.com/PRIS-CV/PMG-Progressive-Multi-Granularity-Training.