Linking Known and Unknown: Generalized Cross-Instance Feature Helps Category Discovery
Zuo, Yuanhao Liu, Yichao Liu, Xiwei Luo, Tingzhang
Zuo, Yuanhao
Liu, Yichao
Liu, Xiwei
Luo, Tingzhang
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
In this paper, we tackle Generalized Category Discovery (GCD) by drawing inspiration from the platypus—a creature that uniquely blends features from different species. Our method bridges the gap between known and unknown categories through a novel cross-instance feature learning paradigm. Unlike traditional GCD methods, we dynamically mix patches from multiple images, integrating features across instances. This process is enhanced by a progressive mixing strategy that evolves from focusing on labeled data to incorporating both labeled and unlabeled data. Complemented by a hierarchical contrastive learning framework that enforces constraints at global, mixed-origin, and inter-mixed levels, our approach effectively generalizes across different feature spaces. Extensive experiments on six benchmark datasets demonstrate our method’s superior performance in recognizing known classes and discovering new ones, setting a new standard in GCD tasks.
Citation
Y. Zuo, Y. Liu, X. Liu and T. Luo, "Linking Known and Unknown: Generalized Cross-Instance Feature Helps Category Discovery," ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5, doi: 10.1109/ICASSP49660.2025.10889500
Source
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Conference
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025
Keywords
Generalized category discovery, semi-supervised learning, contrastive learning
Subjects
Source
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025
Publisher
IEEE