# External Knowledge Injection for CLIP-Based Class-Incremental Learning

arXiv: https://arxiv.org/abs/2503.08510 · HTML: https://mlsanity.com/paper/2503.08510/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 90 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 30 of 63)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)

## Built on by (most cited first, 11 of 11)

- [HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning](https://mlsanity.com/paper/2509.22645/) (2025)
- [C3Box: A CLIP-based Class-Incremental Learning Toolbox](https://mlsanity.com/paper/2601.20852/) (2026)
- [LiteEmbed: Adapting CLIP to Rare Classes](https://mlsanity.com/paper/2601.09661/) (2026)
- [Advancing Analytic Class-Incremental Learning through Vision-Language Calibration](https://mlsanity.com/paper/2602.13670/) (2026)
- [GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning](https://mlsanity.com/paper/2604.17822/) (2026)
- [Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification](https://mlsanity.com/paper/2605.05027/) (2026)
- [Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models](https://mlsanity.com/paper/2605.07512/) (2026)
- [Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning](https://mlsanity.com/paper/2605.13835/) (2026)
- [AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning](https://mlsanity.com/paper/2605.28809/) (2026)
- [Information-Theoretic Decoupled Prompt Tuning for Continual Learning](https://mlsanity.com/paper/2609.26257/) (2026)
- [Visual Branch is What You Need for CLIP-based Class-Incremental Learning](https://mlsanity.com/paper/2609.37888/) (2026)

## Abstract (arXiv)

Class-Incremental Learning (CIL) enables learning systems to continuously adapt to evolving data streams. With the advancement of pre-training, leveraging pre-trained vision-language models (e.g., CLIP) offers a promising starting point for CIL. However, CLIP makes decisions by matching visual embeddings to class names, overlooking the rich contextual information conveyed through language. For instance, the concept of ``cat'' can be decomposed into features like tail, fur, and face for recognition. Besides, since the model is continually updated, these detailed features are overwritten in CIL, requiring external knowledge for compensation. In this paper, we introduce ExterNal knowledGe INjEction (ENGINE) for CLIP-based CIL. To enhance knowledge transfer from outside the dataset, we propose a dual-branch injection tuning framework that encodes informative knowledge from both visual and textual modalities. The visual branch is enhanced with data augmentation to enrich the visual features, while the textual branch leverages GPT-4 to rewrite discriminative descriptors. In addition to this on-the-fly knowledge injection, we also implement post-tuning knowledge by re-ranking the prediction results during inference. With the injected knowledge, the model can better capture informative features for downstream tasks as data evolves. Extensive experiments demonstrate the state-of-the-art performance of ENGINE. Code is available at: https://github.com/LAMDA-CL/ICCV25-ENGINE