Revisiting Mutual Information Maximization for Generalized Category Discovery

TL;DR

This paper introduces RPIM, a novel InfoMax-based approach that enhances generalized category discovery by promoting class independence and using semantic-bias transformation, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper proposes RPIM, a new InfoMax method with pseudo labels and regularization, plus a semantic-bias transformation to improve generalized category discovery.

Findings

RPIM surpasses state-of-the-art by 3.5% on average.

Ensures class independence and uniform distribution improve discovery.

Semantic-bias transformation reduces computational costs.

Abstract

Generalized category discovery presents a challenge in a realistic scenario, which requires the model's generalization ability to recognize unlabeled samples from known and unknown categories. This paper revisits the challenge of generalized category discovery through the lens of information maximization (InfoMax) with a probabilistic parametric classifier. Our findings reveal that ensuring independence between known and unknown classes while concurrently assuming a uniform probability distribution across all classes, yields an enlarged margin among known and unknown classes that promotes the model's performance. To achieve the aforementioned independence, we propose a novel InfoMax-based method, Regularized Parametric InfoMax (RPIM), which adopts pseudo labels to supervise unlabeled samples during InfoMax, while proposing a regularization to ensure the quality of the pseudo labels. Additionally, we introduce novel semantic-bias transformation to refine the features from the pre-trained model instead of direct fine-tuning to rescue the computational costs. Extensive experiments on six benchmark datasets validate the effectiveness of our method. RPIM significantly improves the performance regarding unknown classes, surpassing the state-of-the-art method by an average margin of 3.5%.