Detachedly Learn a Classifier for Class-Incremental Learning

• URL: http://arxiv.org/abs/2302.11730v1
• Date: Thu, 23 Feb 2023 01:35:44 GMT
• Title: Detachedly Learn a Classifier for Class-Incremental Learning
• Authors: Ziheng Li, Shibo Jie, and Zhi-Hong Deng
• Abstract summary: We present an analysis that the failure of vanilla experience replay (ER) comes from unnecessary re-learning of previous tasks and incompetence to distinguish current task from the previous ones. We propose a novel replay strategy task-aware experience replay. Experimental results show our method outperforms current state-of-the-art methods.
• Score: 11.865788374587734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In continual learning, model needs to continually learn a feature extractor and classifier on a sequence of tasks. This paper focuses on how to learn a classifier based on a pretrained feature extractor under continual learning setting. We present an probabilistic analysis that the failure of vanilla experience replay (ER) comes from unnecessary re-learning of previous tasks and incompetence to distinguish current task from the previous ones, which is the cause of knowledge degradation and prediction bias. To overcome these weaknesses, we propose a novel replay strategy task-aware experience replay. It rebalances the replay loss and detaches classifier weight for the old tasks from the update process, by which the previous knowledge is kept intact and the overfitting on episodic memory is alleviated. Experimental results show our method outperforms current state-of-the-art methods.

Related papers

• Reducing Catastrophic Forgetting in Online Class Incremental Learning Using Self-Distillation [3.8506666685467343]
  In continual learning, previous knowledge is forgotten when a model learns new tasks. In this paper, we tried to solve this problem by acquiring transferable knowledge through self-distillation. Our proposed method outperformed conventional methods by experiments on CIFAR10, CIFAR100, and MiniimageNet datasets.
  arXiv  Detail & Related papers  (2024-09-17T16:26:33Z)
• Strike a Balance in Continual Panoptic Segmentation [60.26892488010291]
  We introduce past-class backtrace distillation to balance the stability of existing knowledge with the adaptability to new information. We also introduce a class-proportional memory strategy, which aligns the class distribution in the replay sample set with that of the historical training data. We present a new method named Continual Panoptic Balanced (BalConpas)
  arXiv  Detail & Related papers  (2024-07-23T09:58:20Z)
• 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)
• Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning [64.14254712331116]
  Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. We propose a novel framework of fine-grained knowledge selection and restoration.
  arXiv  Detail & Related papers  (2023-12-20T02:34:11Z)
• Replay-enhanced Continual Reinforcement Learning [37.34722105058351]
  We introduce RECALL, a replay-enhanced method that greatly improves the plasticity of existing replay-based methods on new tasks. Experiments on the Continual World benchmark show that RECALL performs significantly better than purely perfect memory replay.
  arXiv  Detail & Related papers  (2023-11-20T06:21:52Z)
• New Insights on Reducing Abrupt Representation Change in Online Continual Learning [69.05515249097208]
  We focus on the change in representations of observed data that arises when previously unobserved classes appear in the incoming data stream. We show that applying Experience Replay causes the newly added classes' representations to overlap significantly with the previous classes. We propose a new method which mitigates this issue by shielding the learned representations from drastic adaptation to accommodate new classes.
  arXiv  Detail & Related papers  (2022-03-08T01:37:00Z)
• Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship [54.73817402934303]
  We propose Experience Continual Replay (ERR), a bi-level learning framework to adaptively tune task-wise to achieve a better stability plasticity' tradeoff. ERR can consistently improve the performance of all baselines and surpass current state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-31T12:05:22Z)
• An Empirical Investigation of the Role of Pre-training in Lifelong Learning [21.995593026269578]
  We show that generic pre-training implicitly alleviates the effects of catastrophic forgetting when learning multiple tasks sequentially. We study this phenomenon by analyzing the loss landscape, finding that pre-trained weights appear to ease forgetting by leading to wider minima.
  arXiv  Detail & Related papers  (2021-12-16T19:00:55Z)
• Reducing Representation Drift in Online Continual Learning [87.71558506591937]
  We study the online continual learning paradigm, where agents must learn from a changing distribution with constrained memory and compute. In this work we instead focus on the change in representations of previously observed data due to the introduction of previously unobserved class samples in the incoming data stream.
  arXiv  Detail & Related papers  (2021-04-11T15:19:30Z)
• Using Hindsight to Anchor Past Knowledge in Continual Learning [36.271906785418864]
  In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. In this work, we call anchoring, where the learner uses bilevel optimization to update its knowledge on the current task, while keeping intact the predictions on past tasks.
  arXiv  Detail & Related papers  (2020-02-19T13:21:19Z)

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.