Prototypical Exemplar Condensation for Memory-efficient Online Continual Learning

• URL: http://arxiv.org/abs/2603.13804v1
• Date: Sat, 14 Mar 2026 07:24:37 GMT
• Title: Prototypical Exemplar Condensation for Memory-efficient Online Continual Learning
• Abstract summary: Rehearsal-based continual learning mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay.<n>We propose to further compress the memory footprint by synthesizing and storing exemplars, which can form representative prototypes.<n>We introduce a prototypical-based augmentation mechanism that generates synthetic variants of previous data during training, thereby enhancing CL performance.
• Score: 8.074640942193644
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Rehearsal-based continual learning (CL) mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay. Existing studies primarily focus on optimizing memory storage through coreset selection strategies. While these methods are effective, they typically require storing a substantial number of samples per class (SPC), often exceeding 20, to maintain satisfactory performance. In this work, we propose to further compress the memory footprint by synthesizing and storing prototypical exemplars, which can form representative prototypes when passed through the feature extractor. Owing to their representative nature, these exemplars enable the model to retain previous knowledge using only a small number of samples while preserving privacy. Moreover, we introduce a perturbation-based augmentation mechanism that generates synthetic variants of previous data during training, thereby enhancing CL performance. Extensive evaluations on widely used benchmark datasets and settings demonstrate that the proposed algorithm achieves superior performance compared to existing baselines, particularly in scenarios involving large-scale datasets and a high number of tasks.

Related papers

• Unsupervised Continual Learning with Growing Self-Organizing Maps and Synthetic Replay [47.020758735910306]
  This work presents a generative continual learning framework based on growing self-organizing maps (GSOMs) and encoder-decoder models for class-incremental learning.<n>The proposed approach enables exemplar-free replay using distributional statistical memory, which eliminates the need to store raw data.<n>Results across multiple benchmarks show that the proposed approach achieves performance competitive even with supervised state-of-the-art memory-based methods.
  arXiv  Detail & Related papers  (2026-08-27T19:48:44Z)
• The Power of Certainty: How Confident Models Lead to Better Segmentation [0.0]
  We propose a confidence-based self-distillation approach that outperforms state-of-the-art models by utilizing only previous data storage during training.<n>Our approach generalizes well across datasets collected from multiple clinical centers.
  arXiv  Detail & Related papers  (2025-07-14T17:12:43Z)
• Curvature Enhanced Data Augmentation for Regression [4.910937238451485]
  We introduce the Curvature-Enhanced Manifold Sampling (CEMS) method for regression tasks.<n>CEMS delivers superior performance in both in-distribution and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-06-07T16:18:37Z)
• Dynamic Dual Buffer with Divide-and-Conquer Strategy for Online Continual Learning [10.599650191041217]
  Online Continual Learning (OCL) presents a complex learning environment in which new data arrives in a batch-to-batch online format.<n>We introduce an innovative memory framework that incorporates a short-term memory system to retain dynamic information and a long-term memory system to archive enduring knowledge.
  arXiv  Detail & Related papers  (2025-05-23T16:57:04Z)
• Quantifying Memory Utilization with Effective State-Size [73.52115209375343]
  We develop a measure of textitmemory utilization'<n>This metric is tailored to the fundamental class of systems with textitinput-invariant and textitinput-varying linear operators
  arXiv  Detail & Related papers  (2025-04-28T08:12:30Z)
• Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Loss [3.824522034247845]
  Continual learning techniques employ simple replay sample selection processes and use them during subsequent tasks.<n>In this paper, we depart from this by automatically selecting prototypes stored without labels.<n>"Push-away" and "pull-toward" mechanisms are also introduced for class-incremental and domain-incremental scenarios.
  arXiv  Detail & Related papers  (2025-04-09T19:26:26Z)
• A CLIP-Powered Framework for Robust and Generalizable Data Selection [51.46695086779598]
  Real-world datasets often contain redundant and noisy data, imposing a negative impact on training efficiency and model performance.<n>Data selection has shown promise in identifying the most representative samples from the entire dataset.<n>We propose a novel CLIP-powered data selection framework that leverages multimodal information for more robust and generalizable sample selection.
  arXiv  Detail & Related papers  (2024-10-15T03:00:58Z)
• Large-scale Fully-Unsupervised Re-Identification [78.47108158030213]
  We propose two strategies to learn from large-scale unlabeled data. The first strategy performs a local neighborhood sampling to reduce the dataset size in each without violating neighborhood relationships. A second strategy leverages a novel Re-Ranking technique, which has a lower time upper bound complexity and reduces the memory complexity from O(n2) to O(kn) with k n.
  arXiv  Detail & Related papers  (2023-07-26T16:19:19Z)
• Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
  We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
  arXiv  Detail & Related papers  (2023-06-12T15:52:02Z)
• Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning [14.462797749666992]
  We propose a holistic approach to jointly learn the representation and class prototypes. We propose a novel distillation loss that constrains class prototypes to maintain relative similarities as compared to new task data. This method yields state-of-the-art performance in the task-incremental setting.
  arXiv  Detail & Related papers  (2023-03-26T16:35:45Z)
• Memory Replay with Data Compression for Continual Learning [80.95444077825852]
  We propose memory replay with data compression to reduce the storage cost of old training samples. We extensively validate this across several benchmarks of class-incremental learning and in a realistic scenario of object detection for autonomous driving.
  arXiv  Detail & Related papers  (2022-02-14T10:26:23Z)

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.