PDF (4.5 MB)
Collect
Submit Manuscript
Show Outline
Outline
Abstract
Keywords
Show full outline
Hide outline
Research Article | Open Access | Just Accepted

See More, Know More: Richer Prior Knowledge for Novel Class Discovery

1 TK LNDST, College of Computer Science, Nankai University, Tianjin, China.

Show Author Information

Abstract

Novel Class Discovery aims to discover novel categories in an unlabeled dataset by employing a model that is trained on a labeled dataset with different but semantically related categories. The challenge of this task is that the model needs to learn discriminative representations from seen categories that can accurately group unseen categories. Existing methods typically pre-train models on seen data only containing limited semantic categories, resulting in the learned representation less discriminative for varied unseen categories that may be encountered in the future. In this paper, we propose a novel Richer Prior K nowledge (RPK ) module to learn diverse and discriminative representation for future novel categories by exposing the model to a large number of synthetic visual categories. Our insight is that the more categories the model has seen during pre-training, the less biased the learned representation space will be to the base categories. To demonstrate the effectiveness of our approach, we conduct extensive experiments on a variety of datasets and settings, which validates the effectiveness of our proposed method. Additionally, our approach can be easily integrated into other methods and achieves superior performance.

Computational Visual Media
Cite this article:
Peng Z, Wang E, Liu X, et al. See More, Know More: Richer Prior Knowledge for Novel Class Discovery. Computational Visual Media, 2024, https://doi.org/10.26599/CVM.2025.9450446
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return