Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery

TL;DR

This paper introduces an unsupervised class incremental learning method that discovers new categories in unlabeled data without prior knowledge, using proxy anchors to improve feature representation and mitigate forgetting.

Contribution

It presents a novel unsupervised approach combining proxy anchors and clustering for continuous category discovery without labeled data or prior category information.

Findings

Outperforms state-of-the-art methods on fine-grained datasets

Effectively discovers novel categories in unlabeled data

Reduces catastrophic forgetting in incremental learning

Abstract

Recent advances in deep learning have significantly improved the performance of various computer vision applications. However, discovering novel categories in an incremental learning scenario remains a challenging problem due to the lack of prior knowledge about the number and nature of new categories. Existing methods for novel category discovery are limited by their reliance on labeled datasets and prior knowledge about the number of novel categories and the proportion of novel samples in the batch. To address the limitations and more accurately reflect real-world scenarios, in this paper, we propose a novel unsupervised class incremental learning approach for discovering novel categories on unlabeled sets without prior knowledge. The proposed method fine-tunes the feature extractor and proxy anchors on labeled sets, then splits samples into old and novel categories and clusters on the unlabeled dataset. Furthermore, the proxy anchors-based exemplar generates representative category vectors to mitigate catastrophic forgetting. Experimental results demonstrate that our proposed approach outperforms the state-of-the-art methods on fine-grained datasets under real-world scenarios.