External Knowledge Injection for CLIP-Based Class-Incremental Learning
Abstract
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
Cite
@article{arxiv.2503.08510,
title = {External Knowledge Injection for CLIP-Based Class-Incremental Learning},
author = {Da-Wei Zhou and Kai-Wen Li and Jingyi Ning and Han-Jia Ye and Lijun Zhang and De-Chuan Zhan},
journal= {arXiv preprint arXiv:2503.08510},
year = {2025}
}
Comments
Accepted to ICCV 2025. Code is available at: https://github.com/LAMDA-CL/ICCV25-ENGINE