Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data

TL;DR

This paper introduces GAEor, a geometry-guided self-supervised framework that leverages intrinsic geometric features to improve ultra-fine-grained recognition in data-limited scenarios, achieving state-of-the-art results.

Contribution

The paper presents a novel self-supervised approach that captures geometric attributes as recognition cues, enhancing ultra-fine-grained categorization with limited data.

Findings

GAEor achieves new state-of-the-art results on five Ultra-FGVC benchmarks.

Geometric attributes serve as effective recognition cues among highly similar objects.

Amplifying geometry-relevant details improves recognition accuracy.

Abstract

This paper investigates the intrinsic geometrical features of highly similar objects and introduces a general self-supervised framework called the Geometric Attribute Exploration Network (GAEor), which is designed to address the ultra-fine-grained visual categorization (Ultra-FGVC) task in data-limited scenarios. Unlike prior work that often captures subtle yet critical distinctions, GAEor generates geometric attributes as novel alternative recognition cues. These attributes are determined by various details within the object, aligned with its geometric patterns, such as the intricate vein structures in soybean leaves. Crucially, each category exhibits distinct geometric descriptors that serve as powerful cues, even among objects with minimal visual variation -- a factor largely overlooked in recent research. GAEor discovers these geometric attributes by first amplifying geometry-relevant details via visual feedback from a backbone network, then embedding the relative polar coordinates of these details into the final representation. Extensive experiments demonstrate that GAEor significantly sets new state-of-the-art records in five widely-used Ultra-FGVC benchmarks.