Core Concepts
Proposing CiPR framework for better representation learning in GCD through cross-instance positive relations.
Abstract
The content introduces the CiPR framework for Generalized Category Discovery (GCD), addressing the challenge of clustering partially labeled datasets with unknown category numbers. It proposes a novel approach, CiPR, leveraging Cross-instance Positive Relations and a semi-supervised hierarchical clustering algorithm, SNC, to improve representation learning. The method is evaluated on various image recognition datasets, showcasing state-of-the-art performance.
Structure:
Introduction to GCD and its challenges.
Proposed CiPR framework utilizing Cross-instance Positive Relations and SNC algorithm.
Evaluation on generic and fine-grained image recognition datasets.
Comparison with state-of-the-art methods and ablation study on positive relation generation approaches.
Estimation of unknown class numbers and label assignment strategies.
Stats
We propose a new GCD framework named CiPR that achieves 97.7% accuracy on CIFAR-10.
Semi-supervised k-means was adopted for label assignment across all instances in Vaze et al. (2022b).
Our method outperforms existing baselines by 6.2% on CIFAR-10 'All' classes.
Quotes
"We tackle the issue of generalized category discovery (GCD) by drawing inspiration from the baseline method." - Content
"An illustration of the GCD problem is shown in Fig. 1." - Content
"Our method consistently outperforms all others by a significant margin." - Content