Solving the Catastrophic Forgetting Problem in Generalized Category Discovery

• URL: http://arxiv.org/abs/2501.05272v1
• Date: Thu, 09 Jan 2025 14:31:54 GMT
• Title: Solving the Catastrophic Forgetting Problem in Generalized Category Discovery
• Authors: Xinzi Cao, Xiawu Zheng, Guanhong Wang, Weijiang Yu, Yunhang Shen, Ke Li, Yutong Lu, Yonghong Tian,
• Abstract summary: Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets. Recent state-of-the-art method SimGCD transfers the knowledge from known-class data to the learning of novel classes through debiased learning. We propose a novel learning approach, LegoGCD, which is seamlessly integrated into previous methods to enhance the discrimination of novel classes.
• Score: 46.63232918739251
• License:
• Abstract: Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets, providing a more realistic setting for image recognition. Essentially, GCD needs to remember existing patterns thoroughly to recognize novel categories. Recent state-of-the-art method SimGCD transfers the knowledge from known-class data to the learning of novel classes through debiased learning. However, some patterns are catastrophically forgot during adaptation and thus lead to poor performance in novel categories classification. To address this issue, we propose a novel learning approach, LegoGCD, which is seamlessly integrated into previous methods to enhance the discrimination of novel classes while maintaining performance on previously encountered known classes. Specifically, we design two types of techniques termed as Local Entropy Regularization (LER) and Dual-views Kullback Leibler divergence constraint (DKL). The LER optimizes the distribution of potential known class samples in unlabeled data, thus ensuring the preservation of knowledge related to known categories while learning novel classes. Meanwhile, DKL introduces Kullback Leibler divergence to encourage the model to produce a similar prediction distribution of two view samples from the same image. In this way, it successfully avoids mismatched prediction and generates more reliable potential known class samples simultaneously. Extensive experiments validate that the proposed LegoGCD effectively addresses the known category forgetting issue across all datasets, eg, delivering a 7.74% and 2.51% accuracy boost on known and novel classes in CUB, respectively. Our code is available at: https://github.com/Cliffia123/LegoGCD.

Related papers

• Happy: A Debiased Learning Framework for Continual Generalized Category Discovery [54.54153155039062]
  This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD) C-GCD aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. We introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization.
  arXiv  Detail & Related papers  (2024-10-09T04:18:51Z)
• Transfer and Alignment Network for Generalized Category Discovery [11.37283148391564]
  Generalized Category Discovery is a crucial real-world task. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge transfer between labeled and unlabeled data and noisy representation learning on the unlabeled data. We propose a Transfer and Alignment Network (TAN), which incorporates two knowledge transfer mechanisms to calibrate the biased knowledge and two feature alignment mechanisms to learn discriminative features.
  arXiv  Detail & Related papers  (2023-12-27T08:35:47Z)
• MetaGCD: Learning to Continually Learn in Generalized Category Discovery [26.732455383707798]
  We consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data. The goal is to continually discover novel classes while maintaining the performance in known classes. We propose an approach, called MetaGCD, to learn how to incrementally discover with less forgetting.
  arXiv  Detail & Related papers  (2023-08-21T22:16:49Z)
• Dynamic Conceptional Contrastive Learning for Generalized Category Discovery [76.82327473338734]
  Generalized category discovery (GCD) aims to automatically cluster partially labeled data. Unlabeled data contain instances that are not only from known categories of the labeled data but also from novel categories. One effective way for GCD is applying self-supervised learning to learn discriminate representation for unlabeled data. We propose a Dynamic Conceptional Contrastive Learning framework, which can effectively improve clustering accuracy.
  arXiv  Detail & Related papers  (2023-03-30T14:04:39Z)
• PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery [39.03732147384566]
  Generalized Novel Category Discovery (GNCD) setting aims to categorize unlabeled training data coming from known and novel classes. We propose Contrastive Affinity Learning method with auxiliary visual Prompts, dubbed PromptCAL, to address this challenging problem. Our approach discovers reliable pairwise sample affinities to learn better semantic clustering of both known and novel classes for the class token and visual prompts.
  arXiv  Detail & Related papers  (2022-12-11T20:06:14Z)
• Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
  Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
  arXiv  Detail & Related papers  (2022-11-21T18:47:11Z)
• Novel Class Discovery without Forgetting [72.52222295216062]
  We identify and formulate a new, pragmatic problem setting of NCDwF: Novel Class Discovery without Forgetting. We propose a machine learning model to incrementally discover novel categories of instances from unlabeled data. We introduce experimental protocols based on CIFAR-10, CIFAR-100 and ImageNet-1000 to measure the trade-off between knowledge retention and novel class discovery.
  arXiv  Detail & Related papers  (2022-07-21T17:54:36Z)
• Class-incremental Novel Class Discovery [76.35226130521758]
  We study the new task of class-incremental Novel Class Discovery (class-iNCD) We propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes. Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-07-18T13:49:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.