PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning

• URL: http://arxiv.org/abs/2407.14029v1
• Date: Fri, 19 Jul 2024 05:03:16 GMT
• Title: PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning
• Authors: Fei Zhu, Xu-Yao Zhang, Zhen Cheng, Cheng-Lin Liu,
• Abstract summary: Class-incremental learning (CIL) aims to recognize new classes incrementally while maintaining the discriminability of old classes. Most existing CIL methods are exemplar-based, i.e., storing a part of old data for retraining. We present a simple and novel dual bias reduction framework that employs self-supervised transformation (SST) in input space and prototype augmentation (protoAug) in deep feature space.
• Score: 49.240408681098906
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class-incremental learning (CIL) aims to recognize new classes incrementally while maintaining the discriminability of old classes. Most existing CIL methods are exemplar-based, i.e., storing a part of old data for retraining. Without relearning old data, those methods suffer from catastrophic forgetting. In this paper, we figure out two inherent problems in CIL, i.e., representation bias and classifier bias, that cause catastrophic forgetting of old knowledge. To address these two biases, we present a simple and novel dual bias reduction framework that employs self-supervised transformation (SST) in input space and prototype augmentation (protoAug) in deep feature space. On the one hand, SST alleviates the representation bias by learning generic and diverse representations that can transfer across different tasks. On the other hand, protoAug overcomes the classifier bias by explicitly or implicitly augmenting prototypes of old classes in the deep feature space, which poses tighter constraints to maintain previously learned decision boundaries. We further propose hardness-aware prototype augmentation and multi-view ensemble strategies, leading to significant improvements. The proposed framework can be easily integrated with pre-trained models. Without storing any samples of old classes, our method can perform comparably with state-of-the-art exemplar-based approaches which store plenty of old data. We hope to draw the attention of researchers back to non-exemplar CIL by rethinking the necessity of storing old samples in CIL.

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)
• Towards Non-Exemplar Semi-Supervised Class-Incremental Learning [33.560003528712414]
  Class-incremental learning aims to gradually recognize new classes while maintaining the discriminability of old ones. We propose a non-exemplar semi-supervised CIL framework with contrastive learning and semi-supervised incremental prototype classifier (Semi-IPC) Semi-IPC learns a prototype for each class with unsupervised regularization, enabling the model to incrementally learn from partially labeled new data.
  arXiv  Detail & Related papers  (2024-03-27T06:28:19Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration [67.69532794049445]
  We find a tendency for existing methods to misclassify the samples of new classes into base classes, which leads to the poor performance of new classes. We propose a simple yet effective Training-frEE calibratioN (TEEN) strategy to enhance the discriminability of new classes.
  arXiv  Detail & Related papers  (2023-12-08T18:24:08Z)
• Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning [21.901331484173944]
  We analyze the causes of catastrophic forgetting in class incremental learning. We propose a two-stage learning framework with a fixed encoder and an incrementally updated prototype classifier. Our method does not rely on preserved samples of old classes, is thus a non-exemplar based CIL method.
  arXiv  Detail & Related papers  (2023-08-04T14:20:42Z)
• Class-Incremental Learning: A Survey [84.30083092434938]
  Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally. CIL tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. We provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms.
  arXiv  Detail & Related papers  (2023-02-07T17:59:05Z)
• Self-Supervised Class Incremental Learning [51.62542103481908]
  Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time.
  arXiv  Detail & Related papers  (2021-11-18T06:58:19Z)
• Memory-Free Generative Replay For Class-Incremental Learning [32.39857105540859]
  We propose a memory-free generative replay strategy to preserve fine-grained old classes characteristics. Our method is best complemented by prior regularization-based methods proved to be effective for easily distinguishable old classes.
  arXiv  Detail & Related papers  (2021-09-01T12:19:54Z)
• ClaRe: Practical Class Incremental Learning By Remembering Previous Class Representations [9.530976792843495]
  Class Incremental Learning (CIL) tends to learn new concepts perfectly, but not at the expense of performance and accuracy for old data. ClaRe is an efficient solution for CIL by remembering the representations of learned classes in each increment. ClaRe has a better generalization than prior methods thanks to producing diverse instances from the distribution of previously learned classes.
  arXiv  Detail & Related papers  (2021-03-29T10:39:42Z)

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.