Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning

• URL: http://arxiv.org/abs/2508.12692v2
• Date: Fri, 22 Aug 2025 15:58:02 GMT
• Title: Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
• Authors: Taeheon Kim, San Kim, Minhyuk Seo, Dongjae Jeon, Wonje Jeung, Jonghyun Choi,
• Abstract summary: Class-incremental with repetition (CIR) is a more realistic scenario than the traditional class incremental setup.<n>We propose two components that efficiently use the unlabeled data to ensure the high stability and the plasticity of models trained in CIR setup.<n>Both of our proposed components significantly improve the performance in CIR setup, achieving 2nd place in the CVPR 5th CLVISION Challenge.
• Score: 29.379585617313552
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen classes. CIR assumes that we can easily access abundant unlabeled data from external sources, such as the Internet. Therefore, we propose two components that efficiently use the unlabeled data to ensure the high stability and the plasticity of models trained in CIR setup. First, we introduce multi-level knowledge distillation (MLKD) that distills knowledge from multiple previous models across multiple perspectives, including features and logits, so the model can maintain much various previous knowledge. Moreover, we implement dynamic self-supervised loss (SSL) to utilize the unlabeled data that accelerates the learning of new classes, while dynamic weighting of SSL keeps the focus of training to the primary task. Both of our proposed components significantly improve the performance in CIR setup, achieving 2nd place in the CVPR 5th CLVISION Challenge.

Related papers

• Divide and Conquer: Static-Dynamic Collaboration for Few-Shot Class-Incremental Learning [29.237877675710877]
  Few-shot class-incremental learning aims to continuously recognize novel classes under limited data.<n>We propose a framework termed Static-Dynamic Collaboration to achieve a better trade-off between stability and plasticity.<n>By employing both stages, our method achieves improved retention of old knowledge while continuously adapting to new classes.
  arXiv  Detail & Related papers  (2026-01-13T11:18:43Z)
• Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts [59.615381619866284]
  Domain-Incremental Learning (DIL) focuses on continual learning in non-stationary environments.<n>DIL faces two critical challenges in the context of imbalanced data: intra-domain class imbalance and cross-domain class distribution shifts.<n>We introduce the Dual-Balance Collaborative Experts (DCE) framework to overcome these challenges.
  arXiv  Detail & Related papers  (2025-07-09T17:57:07Z)
• DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning [22.386864304549285]
  Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands.<n>Recent rehearsal-free methods employ model-based and regularization-based strategies to address this issue.<n>We propose a $textbfD$e $textbfA$ttention-based $textbfTask $textbfA$daptation ( DATA)<n> DATA explicitly decouples and learns both task-specific and task-shared knowledge using high-rank and low-rank task adapters.
  arXiv  Detail & Related papers  (2025-02-17T06:35:42Z)
• CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning [62.69917996026769]
  A class-incremental learning task requires learning and preserving both spatial appearance and temporal action involvement.<n>We propose a framework that equips separate adapters to learn new class patterns, accommodating the incremental information requirements unique to each class.<n>A causal compensation mechanism is proposed to reduce the conflicts during increment and memorization for between different types of information.
  arXiv  Detail & Related papers  (2025-01-13T11:34:55Z)
• Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning [79.46570165281084]
  We propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks.
  arXiv  Detail & Related papers  (2024-11-11T07:36:19Z)
• KIF: Knowledge Identification and Fusion for Language Model Continual Learning [41.28933724210434]
  We introduce a novel framework for language models, named Knowledge Identification and Fusion (KIF)<n>KIF segregates the model into'skill units' based on parameter dependencies, allowing for more precise control.<n>It employs a novel group-wise knowledge identification technique to ascertain the importance distribution of skill units for a new task.<n>As a result, KIF achieves an optimal balance between retaining prior knowledge and excelling in new tasks.
  arXiv  Detail & Related papers  (2024-08-09T17:44:45Z)
• Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters [65.15700861265432]
  We present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters. To preserve the zero-shot recognition capability of vision-language models, we introduce a Distribution Discriminative Auto-Selector.
  arXiv  Detail & Related papers  (2024-03-18T08:00:23Z)
• DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning [19.717868805172323]
  We propose an active data filtering process during self-supervised pre-training in our novel framework, Duplicate Elimination (DUEL) This framework integrates an active memory inspired by human working memory and introduces distinctiveness information, which measures the diversity of the data in the memory. The DUEL policy, which replaces the most duplicated data with new samples, aims to enhance the distinctiveness information in the memory and thereby mitigate class imbalances.
  arXiv  Detail & Related papers  (2024-02-14T06:09:36Z)
• Towards Plastic and Stable Exemplar-Free Incremental Learning: A Dual-Learner Framework with Cumulative Parameter Averaging [12.168402195820649]
  We propose a Dual-Learner framework with Cumulative. Averaging (DLCPA) We show that DLCPA outperforms several state-of-the-art exemplar-free baselines in both Task-IL and Class-IL settings.
  arXiv  Detail & Related papers  (2023-10-28T08:48:44Z)
• Evolving Knowledge Mining for Class Incremental Segmentation [113.59611699693092]
  Class Incremental Semantic (CISS) has been a trend recently due to its great significance in real-world applications. We propose a novel method, Evolving kNowleDge minING, employing a frozen backbone. We evaluate our method on two widely used benchmarks and consistently demonstrate new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-06-03T07:03:15Z)
• 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)

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.