Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning

• URL: http://arxiv.org/abs/2501.00237v1
• Date: Tue, 31 Dec 2024 03:02:20 GMT
• Title: Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning
• Authors: Wei Chen, Yi Zhou,
• Abstract summary: We propose a simple yet effective method named DisCo to deal with class-incremental learning tasks. DisCo can be easily integrated into existing state-of-the-art class-incremental learning methods. Experimental results show that incorporating our method into various CIL methods achieves substantial performance improvements.
• Score: 9.712093262192733
• License:
• Abstract: In the realm of class-incremental learning (CIL), alleviating the catastrophic forgetting problem is a pivotal challenge. This paper discovers a counter-intuitive observation: by incorporating domain shift into CIL tasks, the forgetting rate is significantly reduced. Our comprehensive studies demonstrate that incorporating domain shift leads to a clearer separation in the feature distribution across tasks and helps reduce parameter interference during the learning process. Inspired by this observation, we propose a simple yet effective method named DisCo to deal with CIL tasks. DisCo introduces a lightweight prototype pool that utilizes contrastive learning to promote distinct feature distributions for the current task relative to previous ones, effectively mitigating interference across tasks. DisCo can be easily integrated into existing state-of-the-art class-incremental learning methods. Experimental results show that incorporating our method into various CIL methods achieves substantial performance improvements, validating the benefits of our approach in enhancing class-incremental learning by separating feature representation and reducing interference. These findings illustrate that DisCo can serve as a robust fashion for future research in class-incremental learning.

Related papers

• CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning [52.63674911541416]
  Few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and forgetting. Our primary focus is representation learning on base classes to tackle the unique challenge of FSCIL. We find that trying to secure the spread of features within a more confined feature space enables the learned representation to strike a better balance between transferability and discriminability.
  arXiv  Detail & Related papers  (2024-10-08T02:23:16Z)
• Joint Input and Output Coordination for Class-Incremental Learning [84.36763449830812]
  We propose a joint input and output coordination (JIOC) mechanism to address these issues. This mechanism assigns different weights to different categories of data according to the gradient of the output score. It can be incorporated into different incremental learning approaches that use memory storage.
  arXiv  Detail & Related papers  (2024-09-09T13:55:07Z)
• Mitigating Interference in the Knowledge Continuum through Attention-Guided Incremental Learning [17.236861687708096]
  Attention-Guided Incremental Learning' (AGILE) is a rehearsal-based CL approach that incorporates compact task attention to effectively reduce interference between tasks. AGILE significantly improves generalization performance by mitigating task interference and outperforming rehearsal-based approaches in several CL scenarios.
  arXiv  Detail & Related papers  (2024-05-22T20:29:15Z)
• Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness [3.0620294646308754]
  We introduce an effective-Rank based Feature Richness enhancement (RFR) method, designed for improving forward compatibility. Our results demonstrate the effectiveness of our approach in enhancing novel-task performance while mitigating catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-03-22T11:14:30Z)
• Relaxed Contrastive Learning for Federated Learning [48.96253206661268]
  We propose a novel contrastive learning framework to address the challenges of data heterogeneity in federated learning. Our framework outperforms all existing federated learning approaches by huge margins on the standard benchmarks.
  arXiv  Detail & Related papers  (2024-01-10T04:55:24Z)
• Clustering-based Domain-Incremental Learning [4.835091081509403]
  Key challenge in continual learning is the so-called "catastrophic forgetting problem" We propose an online clustering-based approach on a dynamically updated finite pool of samples or gradients. We demonstrate the effectiveness of the proposed strategy and its promising performance compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-21T13:49:05Z)
• Knowledge Diffusion for Distillation [53.908314960324915]
  The representation gap between teacher and student is an emerging topic in knowledge distillation (KD) We state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature. We propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models.
  arXiv  Detail & Related papers  (2023-05-25T04:49:34Z)
• Contrastive Continual Learning with Feature Propagation [32.70482982044965]
  Continual machine learners are elaborated to commendably learn a stream of tasks with domain and class shifts among different tasks. We propose a general feature-propagation based contrastive continual learning method which is capable of handling multiple continual learning scenarios.
  arXiv  Detail & Related papers  (2021-12-03T04:55:28Z)
• Incremental Embedding Learning via Zero-Shot Translation [65.94349068508863]
  Current state-of-the-art incremental learning methods tackle catastrophic forgetting problem in traditional classification networks. We propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI) In addition, ZSTCI can easily be combined with existing regularization-based incremental learning methods to further improve performance of embedding networks.
  arXiv  Detail & Related papers  (2020-12-31T08:21:37Z)
• Task-Feature Collaborative Learning with Application to Personalized Attribute Prediction [166.87111665908333]
  We propose a novel multi-task learning method called Task-Feature Collaborative Learning (TFCL) Specifically, we first propose a base model with a heterogeneous block-diagonal structure regularizer to leverage the collaborative grouping of features and tasks. As a practical extension, we extend the base model by allowing overlapping features and differentiating the hard tasks.
  arXiv  Detail & Related papers  (2020-04-29T02:32:04Z)

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.