CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay

• URL: http://arxiv.org/abs/2402.01348v2
• Date: Tue, 9 Apr 2024 08:33:22 GMT
• Title: CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay
• Authors: Jianshu Zhang, Yankai Fu, Ziheng Peng, Dongyu Yao, Kun He,
• Abstract summary: COgnitive REplay (CORE) draws inspiration from human cognitive review processes. CORE achieves an average accuracy of 37.95% on split-CIFAR10, surpassing the best baseline method by 6.52%. It significantly enhances the accuracy of the poorest-performing task by 6.30% compared to the top baseline.
• Score: 14.169588352209907
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces a novel perspective to significantly mitigate catastrophic forgetting in continuous learning (CL), which emphasizes models' capacity to preserve existing knowledge and assimilate new information. Current replay-based methods treat every task and data sample equally and thus can not fully exploit the potential of the replay buffer. In response, we propose COgnitive REplay (CORE), which draws inspiration from human cognitive review processes. CORE includes two key strategies: Adaptive Quantity Allocation and Quality-Focused Data Selection. The former adaptively modulates the replay buffer allocation for each task based on its forgetting rate, while the latter guarantees the inclusion of representative data that best encapsulates the characteristics of each task within the buffer. Our approach achieves an average accuracy of 37.95% on split-CIFAR10, surpassing the best baseline method by 6.52%. Additionally, it significantly enhances the accuracy of the poorest-performing task by 6.30% compared to the top baseline. Code is available at https://github.com/sterzhang/CORE.

Related papers

• Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation [37.36913210031282]
  Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. We propose SEER, an efficient PbRL method that integrates label smoothing and policy regularization techniques.
  arXiv  Detail & Related papers  (2024-05-29T01:49:20Z)
• Adaptive Rentention & Correction for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task. We name our approach Adaptive Retention & Correction (ARC) ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• 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)
• Class-Wise Buffer Management for Incremental Object Detection: An Effective Buffer Training Strategy [11.109975137910881]
  Class incremental learning aims to solve a problem that arises when continuously adding unseen class instances to an existing model. We introduce an effective buffer training strategy (eBTS) that creates the optimized replay buffer on object detection.
  arXiv  Detail & Related papers  (2023-12-14T17:10:09Z)
• DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection [72.25697820290502]
  This work introduces a straightforward and efficient strategy to identify potential novel classes through zero-shot classification. We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training. Empirical evaluations on three datasets, including LVIS, V3Det, and COCO, demonstrate significant improvements over the baseline performance.
  arXiv  Detail & Related papers  (2023-10-02T17:52:24Z)
• OER: Offline Experience Replay for Continual Offline Reinforcement Learning [25.985985377992034]
  Continuously learning new skills via a sequence of pre-collected offline datasets is desired for an agent. In this paper, we formulate a new setting, continual offline reinforcement learning (CORL), where an agent learns a sequence of offline reinforcement learning tasks. We propose a new model-based experience selection scheme to build the replay buffer, where a transition model is learned to approximate the state distribution.
  arXiv  Detail & Related papers  (2023-05-23T08:16:44Z)
• SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model [73.80068155830708]
  We present an extensive analysis for continual learning on a pre-trained model (CLPM) We propose a simple but extremely effective approach named Slow Learner with Alignment (SLCA) Across a variety of scenarios, our proposal provides substantial improvements for CLPM.
  arXiv  Detail & Related papers  (2023-03-09T08:57:01Z)
• Improving information retention in large scale online continual learning [99.73847522194549]
  Online continual learning aims to adapt efficiently to new data while retaining existing knowledge. Recent work suggests that information retention remains a problem in large scale OCL even when the replay buffer is unlimited. We propose using a moving average family of methods to improve optimization for non-stationary objectives.
  arXiv  Detail & Related papers  (2022-10-12T16:59:43Z)
• Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification [57.36281142038042]
  We present a new adaptive block called Contextual Squeeze-and-Excitation (CaSE) that adjusts a pretrained neural network on a new task to significantly improve performance. We also present a new training protocol based on Coordinate-Descent called UpperCaSE that exploits meta-trained CaSE blocks and fine-tuning routines for efficient adaptation.
  arXiv  Detail & Related papers  (2022-06-20T15:25:08Z)
• GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning [1.911678487931003]
  We show significant gains (2%-4% absolute) over the state-of-the-art in the well-studied offline continual learning setting. Our findings also effectively transfer to online / streaming CL settings, showing upto 5% gains over existing approaches.
  arXiv  Detail & Related papers  (2021-11-18T18:01:57Z)
• Generative Feature Replay with Orthogonal Weight Modification for Continual Learning [20.8966035274874]
  generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting. We propose to replay penultimate layer feature with a generative model; 2) leverage a self-supervised auxiliary task to further enhance the stability of feature. Empirical results on several datasets show our method always achieves substantial improvement over powerful OWM.
  arXiv  Detail & Related papers  (2020-05-07T13:56:22Z)

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.