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

arXiv: https://arxiv.org/abs/2508.12692 · HTML: https://mlsanity.com/paper/2508.12692/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Distillation for continual learning, one of 12 directions in Knowledge distillation.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 18 Aug 2025.

## Placed in

- Knowledge distillation / [Distillation for continual learning](https://mlsanity.com/distill/distillation-for-continual-learning/)

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Class-Incremental Continual Learning into the eXtended DER-verse](https://mlsanity.com/paper/2201.00766/) (2022)
- [Online Coreset Selection for Rehearsal-based Continual Learning](https://mlsanity.com/paper/2106.01085/) (2021)
- [On the duality between contrastive and non-contrastive self-supervised learning](https://mlsanity.com/paper/2206.02574/) (2022)
- [Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay](https://mlsanity.com/paper/2207.11213/) (2022)
- [R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning](https://mlsanity.com/paper/2203.13104/) (2022)
- [Online Continual Learning Without the Storage Constraint](https://mlsanity.com/paper/2305.09253/) (2023)
- [Learning Equi-angular Representations for Online Continual Learning](https://mlsanity.com/paper/2404.01628/) (2024)
- [Class-Incremental Learning with Repetition](https://mlsanity.com/paper/2301.11396/) (2023)
- [Tag Your Fish in the Broken Net: A Responsible Web Framework for Protecting Online Privacy and Copyright](https://mlsanity.com/paper/2310.07915/) (2023)

## Abstract (arXiv)

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.