Novel Class Discovery for Ultra-Fine-Grained Visual Categorization

TL;DR

This paper introduces a novel task called Ultra-Fine-Grained Novel Class Discovery (UFG-NCD) for ultra-fine-grained visual categorization, proposing a Region-Aligned Proxy Learning framework that leverages partially labeled data to identify new categories with improved accuracy.

Contribution

The paper presents a new task UFG-NCD and a Region-Aligned Proxy Learning framework with CRA and SemiPL modules, advancing ultra-fine-grained visual categorization without extensive human annotation.

Findings

RAPL outperforms baseline methods on multiple datasets.

CRA effectively captures discriminative local features.

SemiPL enhances knowledge transfer and representation learning.

Abstract

Ultra-fine-grained visual categorization (Ultra-FGVC) aims at distinguishing highly similar sub-categories within fine-grained objects, such as different soybean cultivars. Compared to traditional fine-grained visual categorization, Ultra-FGVC encounters more hurdles due to the small inter-class and large intra-class variation. Given these challenges, relying on human annotation for Ultra-FGVC is impractical. To this end, our work introduces a novel task termed Ultra-Fine-Grained Novel Class Discovery (UFG-NCD), which leverages partially annotated data to identify new categories of unlabeled images for Ultra-FGVC. To tackle this problem, we devise a Region-Aligned Proxy Learning (RAPL) framework, which comprises a Channel-wise Region Alignment (CRA) module and a Semi-Supervised Proxy Learning (SemiPL) strategy. The CRA module is designed to extract and utilize discriminative features from local regions, facilitating knowledge transfer from labeled to unlabeled classes. Furthermore, SemiPL strengthens representation learning and knowledge transfer with proxy-guided supervised learning and proxy-guided contrastive learning. Such techniques leverage class distribution information in the embedding space, improving the mining of subtle differences between labeled and unlabeled ultra-fine-grained classes. Extensive experiments demonstrate that RAPL significantly outperforms baselines across various datasets, indicating its effectiveness in handling the challenges of UFG-NCD. Code is available at https://github.com/SSDUT-Caiyq/UFG-NCD.