Unleashing the Potential of Model Bias for Generalized Category Discovery

TL;DR

This paper introduces Self-Debiasing Calibration (SDC), a novel framework that leverages model bias to improve the discovery of both known and unknown categories in unlabeled data, outperforming existing methods.

Contribution

The paper proposes SDC, a new approach that transforms model bias into a tool for better generalized category discovery, addressing bias and confusion issues effectively.

Findings

SDC outperforms state-of-the-art methods on benchmark datasets.

SDC improves accuracy in identifying novel categories.

The approach effectively reduces category bias and confusion.

Abstract

Generalized Category Discovery is a significant and complex task that aims to identify both known and undefined novel categories from a set of unlabeled data, leveraging another labeled dataset containing only known categories. The primary challenges stem from model bias induced by pre-training on only known categories and the lack of precise supervision for novel ones, leading to category bias towards known categories and category confusion among different novel categories, which hinders models' ability to identify novel categories effectively. To address these challenges, we propose a novel framework named Self-Debiasing Calibration (SDC). Unlike prior methods that regard model bias towards known categories as an obstacle to novel category identification, SDC provides a novel insight into unleashing the potential of the bias to facilitate novel category learning. Specifically, the output of the biased model serves two key purposes. First, it provides an accurate modeling of category bias, which can be utilized to measure the degree of bias and debias the output of the current training model. Second, it offers valuable insights for distinguishing different novel categories by transferring knowledge between similar categories. Based on these insights, SDC dynamically adjusts the output logits of the current training model using the output of the biased model. This approach produces less biased logits to effectively address the issue of category bias towards known categories, and generates more accurate pseudo labels for unlabeled data, thereby mitigating category confusion for novel categories. Experiments on three benchmark datasets show that SDC outperforms SOTA methods, especially in the identification of novel categories. Our code and data are available at \url{https://github.com/Lackel/SDC}.