Dynamic Residual Classifier for Class Incremental Learning

• URL: http://arxiv.org/abs/2308.13305v1
• Date: Fri, 25 Aug 2023 11:07:11 GMT
• Title: Dynamic Residual Classifier for Class Incremental Learning
• Authors: Xiuwei Chen, Xiaobin Chang
• Abstract summary: With imbalanced sample numbers between old and new classes, the learning can be biased. Existing CIL methods exploit the longtailed (LT) recognition techniques, e.g., the adjusted losses and the data re-sampling methods. A novel Dynamic Residual adaptation (DRC) is proposed to handle this challenging scenario.
• Score: 4.02487511510606
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the classifier learning can be biased. Existing CIL methods exploit the long-tailed (LT) recognition techniques, e.g., the adjusted losses and the data re-sampling methods, to handle the data imbalance issue within each increment task. In this work, the dynamic nature of data imbalance in CIL is shown and a novel Dynamic Residual Classifier (DRC) is proposed to handle this challenging scenario. Specifically, DRC is built upon a recent advance residual classifier with the branch layer merging to handle the model-growing problem. Moreover, DRC is compatible with different CIL pipelines and substantially improves them. Combining DRC with the model adaptation and fusion (MAF) pipeline, this method achieves state-of-the-art results on both the conventional CIL and the LT-CIL benchmarks. Extensive experiments are also conducted for a detailed analysis. The code is publicly available.

Related papers

• Heterogeneous Learning Rate Scheduling for Neural Architecture Search on Long-Tailed Datasets [0.0]
  We propose a novel adaptive learning rate scheduling strategy tailored for the architecture parameters of DARTS. Our approach dynamically adjusts the learning rate of the architecture parameters based on the training epoch, preventing the disruption of well-trained representations.
  arXiv  Detail & Related papers  (2024-06-11T07:32:25Z)
• Coordinated Sparse Recovery of Label Noise [2.9495895055806804]
  This study focuses on robust classification tasks where the label noise is instance-dependent. We propose a method called Coordinated Sparse Recovery (CSR) CSR introduces a collaboration matrix and confidence weights to coordinate model predictions and noise recovery, reducing error leakage. Based on CSR, this study designs a joint sample selection strategy and constructs a comprehensive and powerful learning framework called CSR+.
  arXiv  Detail & Related papers  (2024-04-07T03:41:45Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• 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)
• Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion [50.03041373044267]
  We propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Learning. Experiments show that CFL achieves state-of-the-art performance and has a stronger ability to overcome compared with the classification baselines.
  arXiv  Detail & Related papers  (2023-05-20T19:22:40Z)
• Continual Learning with Optimal Transport based Mixture Model [17.398605698033656]
  We propose an online mixture model learning approach based on nice properties of the mature optimal transport theory (OT-MM) Our proposed method can significantly outperform the current state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-11-30T06:40:29Z)
• 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)
• Learning convex regularizers satisfying the variational source condition for inverse problems [4.2917182054051]
  We propose adversarial convex regularization (ACR) to learn data-driven convex regularizers via adversarial training. We leverage the variational source condition (SC) during training to enforce that the ground-truth images minimize the variational loss corresponding to the learned convex regularizer. The resulting regularizer (ACR-SC) performs on par with the ACR, but unlike ACR, comes with a quantitative convergence rate estimate.
  arXiv  Detail & Related papers  (2021-10-24T20:05:59Z)
• Task-agnostic Continual Learning with Hybrid Probabilistic Models [75.01205414507243]
  We propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification. The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting. We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.
  arXiv  Detail & Related papers  (2021-06-24T05:19:26Z)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)
• The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis [36.298869931803836]
  Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase. We propose a robust classifier with attentive relation routing, which assigns soft weights by automatically aggregating the relations.
  arXiv  Detail & Related papers  (2020-09-15T12:47:00Z)

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.