Relational Retrieval: Leveraging Known-Novel Interactions for Generalized Category Discovery
cs.CV, cs.AI, cs.MM
Submitted: 2026-05-10
Updated: 2026-09-19
Comments: Accepted at ICMR 2026
Journal ref: Proceedings of the 2026 ACM International Conference on Multimedia Retrieval (ICMR '26), pp. 410-414, 2026
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: In this study, we tackle Generalized Category Discovery (GCD) via a Relational Retrieval perspective, explicitly coupling labeled and unlabeled data through bidirectional knowledge transfer.
Terminology
Abstract
In this study, we tackle Generalized Category Discovery (GCD) via a Relational Retrieval perspective, explicitly coupling labeled and unlabeled data through bidirectional knowledge transfer. While existing methods treat these sources separately, missing valuable interaction opportunities, we propose Relational Pattern Consistency (RPC) that enables mutual enhancement. RPC employs One-vs-All classifiers for soft ID/OOD decomposition, then introduces two mechanisms: (i) for known-class preservation, we transfer semantic behavioral alignment; (ii) for category discovery, we leverage the insight that samples from the same category maintain invariant relationships with known-class prototypes, transforming unreliable pseudo-labeling into well-defined relational pattern matching. This bidirectional design allows labeled data to guide unlabeled learning while discovering novel categories through their collective relational signatures. Extensive experiments demonstrate RPC achieves state-of-the-art performance on both generic and fine-grained benchmarks.
Sources
- Category Discovery: An Open-World Perspective
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning
- DIG-FACE: De-biased Learning for Generalized Facial Expression Category Discovery
- Fine-Grained Visual Classification of Aircraft
- A Survey on Multimodal Wearable Sensor-based Human Action Recognition
- FaceGCD: Generalized Face Discovery via Dynamic Prefix Generation
- Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models