# CLIP model is an Efficient Continual Learner

arXiv: https://arxiv.org/abs/2210.03114 · HTML: https://mlsanity.com/paper/2210.03114/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 61 references that are in the map.
- First posted on arXiv 6 Oct 2022.

## Builds on (most cited first, 30 of 47)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [DER: Dynamically Expandable Representation for Class Incremental Learning](https://mlsanity.com/paper/2103.16788/) (2021)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)

## Built on by (most cited first, 30 of 65)

- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2303.06628/) (2023)
- [Fine-tuning can cripple your foundation model; preserving features may be the solution](https://mlsanity.com/paper/2308.13320/) (2023)
- [CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not](https://mlsanity.com/paper/2303.13440/) (2023)
- [Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization](https://mlsanity.com/paper/2302.00624/) (2023)
- [Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion](https://mlsanity.com/paper/2407.14143/) (2024)
- [AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning](https://mlsanity.com/paper/2305.11488/) (2023)
- [PIVOT: Prompting for Video Continual Learning](https://mlsanity.com/paper/2212.04842/) (2022)
- [TiC-CLIP: Continual Training of CLIP Models](https://mlsanity.com/paper/2310.16226/) (2023)
- [A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm](https://mlsanity.com/paper/2310.12244/) (2023)
- [CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation](https://mlsanity.com/paper/2308.07146/) (2023)
- [Language Guided Concept Bottleneck Models for Interpretable Continual Learning](https://mlsanity.com/paper/2503.23283/) (2025)
- [AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving](https://mlsanity.com/paper/2403.17373/) (2024)
- [CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models](https://mlsanity.com/paper/2403.19137/) (2024)
- [NLLB-CLIP -- train performant multilingual image retrieval model on a budget](https://mlsanity.com/paper/2309.01859/) (2023)
- [VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model](https://mlsanity.com/paper/2403.05346/) (2024)
- [Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data](https://mlsanity.com/paper/2310.05010/) (2023)
- [Generative Multi-modal Models are Good Class-Incremental Learners](https://mlsanity.com/paper/2403.18383/) (2024)
- [Multimodal Parameter-Efficient Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2303.04751/) (2023)
- [CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning](https://mlsanity.com/paper/2407.15793/) (2024)
- [Towards General Purpose Medical AI: Continual Learning Medical Foundation Model](https://mlsanity.com/paper/2303.06580/) (2023)
- [Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2401.01598/) (2024)
- [DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions](https://mlsanity.com/paper/2502.05091/) (2025)
- [Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning](https://mlsanity.com/paper/2401.17186/) (2024)
- [World Engine: Towards the Era of Post-Training for Autonomous Driving](https://mlsanity.com/paper/2606.19836/) (2026)
- [Prompt Algebra for Task Composition](https://mlsanity.com/paper/2306.00310/) (2023)
- [Towards Incremental Learning in Large Language Models: A Critical Review](https://mlsanity.com/paper/2404.18311/) (2024)
- [Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning](https://mlsanity.com/paper/2408.01076/) (2024)
- [Brain-inspired continual pre-trained learner via silent synaptic consolidation](https://mlsanity.com/paper/2410.05899/) (2024)
- [Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors](https://mlsanity.com/paper/2505.20680/) (2025)

## Abstract (arXiv)

The continual learning setting aims to learn new tasks over time without forgetting the previous ones. The literature reports several significant efforts to tackle this problem with limited or no access to previous task data. Among such efforts, typical solutions offer sophisticated techniques involving memory replay, knowledge distillation, model regularization, and dynamic network expansion. The resulting methods have a retraining cost at each learning task, dedicated memory requirements, and setting-specific design choices. In this work, we show that a frozen CLIP (Contrastive Language-Image Pretraining) model offers astounding continual learning performance without any fine-tuning (zero-shot evaluation). We evaluate CLIP under a variety of settings including class-incremental, domain-incremental and task-agnostic incremental learning on five popular benchmarks (ImageNet-100 & 1K, CORe50, CIFAR-100, and TinyImageNet). Without any bells and whistles, the CLIP model outperforms the state-of-the-art continual learning approaches in the majority of the settings. We show the effect on the CLIP model's performance by varying text inputs with simple prompt templates. To the best of our knowledge, this is the first work to report the CLIP zero-shot performance in a continual setting. We advocate the use of this strong yet embarrassingly simple baseline for future comparisons in the continual learning tasks.