Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery
This addresses the challenge of classifying unlabeled data with both seen and novel categories in fine-grained domains, representing an incremental improvement over prior GCD methods.
The paper tackles the problem of Generalized Category Discovery (GCD) in fine-grained scenarios, where existing methods struggle due to reliance on global features, and proposes PartGCD to incorporate part knowledge, achieving state-of-the-art performance on fine-grained benchmarks while remaining competitive on generic datasets.
Generalized Category Discovery (GCD) aims to classify unlabeled data containing both seen and novel categories. Although existing methods perform well on generic datasets, they struggle in fine-grained scenarios. We attribute this difficulty to their reliance on contrastive learning over global image features to automatically capture discriminative cues, which fails to capture the subtle local differences essential for distinguishing fine-grained categories. Therefore, in this paper, we propose incorporating part knowledge to address fine-grained GCD, which introduces two key challenges: the absence of annotations for novel classes complicates the extraction of the part features, and global contrastive learning prioritizes holistic feature invariance, inadvertently suppressing discriminative local part patterns. To address these challenges, we propose PartGCD, including 1) Adaptive Part Decomposition, which automatically extracts class-specific semantic parts via Gaussian Mixture Models, and 2) Part Discrepancy Regularization, enforcing explicit separation between part features to amplify fine-grained local part distinctions. Experiments demonstrate state-of-the-art performance across multiple fine-grained benchmarks while maintaining competitiveness on generic datasets, validating the effectiveness and robustness of our approach.