Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery2025
- Textual Knowledge Matters: Cross-Modality Co-teaching for Generalized Visual Class Discovery2024
- No Representation Rules Them All in Category Discovery2023
- SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning2022
- Explanation recruits comparison in a category-learning taskCognition, 2019
- 3D Object Representations for Fine-Grained Categorization2013