# Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuning

arXiv: https://arxiv.org/abs/2303.17235 · HTML: https://mlsanity.com/paper/2303.17235/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 40 references that are in the map.
- First posted on arXiv 30 Mar 2023.

## Builds on (most cited first, 30 of 34)

- [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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Large Batch Training of Convolutional Networks](https://mlsanity.com/paper/1708.03888/) (2017)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [Co2L: Contrastive Continual Learning](https://mlsanity.com/paper/2106.14413/) (2021)
- [Selective Experience Replay for Lifelong Learning](https://mlsanity.com/paper/1802.10269/) (2018)
- [Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines](https://mlsanity.com/paper/1810.12488/) (2018)
- [Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning](https://mlsanity.com/paper/1904.03137/) (2019)
- [Self-Supervised Models are Continual Learners](https://mlsanity.com/paper/2112.04215/) (2021)

## Built on by (most cited first, 16 of 16)

- [ViLCo-Bench: VIdeo Language COntinual learning Benchmark](https://mlsanity.com/paper/2406.13123/) (2024)
- [Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning](https://mlsanity.com/paper/2306.05101/) (2023)
- [Memory-efficient Continual Learning with Neural Collapse Contrastive](https://mlsanity.com/paper/2412.02865/) (2024)
- [An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2308.11677/) (2023)
- [Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning](https://mlsanity.com/paper/2403.18266/) (2024)
- [CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning](https://mlsanity.com/paper/2407.12188/) (2024)
- [Balancing Continual Learning and Fine-tuning for Human Activity Recognition](https://mlsanity.com/paper/2401.02255/) (2024)
- [Replay to Remember (R2R): An Efficient Uncertainty-driven Unsupervised Continual Learning Framework Using Generative Replay](https://mlsanity.com/paper/2505.04787/) (2025)
- [Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning](https://mlsanity.com/paper/2505.14125/) (2025)
- [CRoP: Context-wise Robust Static Human-Sensing Personalization](https://mlsanity.com/paper/2409.17994/) (2024)
- [Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training](https://mlsanity.com/paper/2509.17816/) (2025)
- [CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable Systems](https://mlsanity.com/paper/2509.23077/) (2025)
- [SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse](https://mlsanity.com/paper/2510.15751/) (2025)
- [CL-BioGAN: Biologically-Inspired Cross-Domain Continual Learning for Hyperspectral Anomaly Detection](https://mlsanity.com/paper/2505.11796/) (2025)
- [MoRe: Modular Representations for Principled Continual Representation Learning on Sequential Data](https://mlsanity.com/paper/2605.14364/) (2026)
- [Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models](https://mlsanity.com/paper/2607.09785/) (2026)

## Abstract (arXiv)

Self-supervised learning (SSL) has shown remarkable performance in computer vision tasks when trained offline. However, in a Continual Learning (CL) scenario where new data is introduced progressively, models still suffer from catastrophic forgetting. Retraining a model from scratch to adapt to newly generated data is time-consuming and inefficient. Previous approaches suggested re-purposing self-supervised objectives with knowledge distillation to mitigate forgetting across tasks, assuming that labels from all tasks are available during fine-tuning. In this paper, we generalize self-supervised continual learning in a practical setting where available labels can be leveraged in any step of the SSL process. With an increasing number of continual tasks, this offers more flexibility in the pre-training and fine-tuning phases. With Kaizen, we introduce a training architecture that is able to mitigate catastrophic forgetting for both the feature extractor and classifier with a carefully designed loss function. By using a set of comprehensive evaluation metrics reflecting different aspects of continual learning, we demonstrated that Kaizen significantly outperforms previous SSL models in competitive vision benchmarks, with up to 16.5% accuracy improvement on split CIFAR-100. Kaizen is able to balance the trade-off between knowledge retention and learning from new data with an end-to-end model, paving the way for practical deployment of continual learning systems.