External Knowledge Injection for CLIP-Based Class-Incremental Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Da-Wei, Li, Kai-Wen, Ning, Jingyi, Ye, Han-Jia, Zhang, Lijun, Zhan, De-Chuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915407179284480
author Zhou, Da-Wei
Li, Kai-Wen
Ning, Jingyi
Ye, Han-Jia
Zhang, Lijun
Zhan, De-Chuan
author_facet Zhou, Da-Wei
Li, Kai-Wen
Ning, Jingyi
Ye, Han-Jia
Zhang, Lijun
Zhan, De-Chuan
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2503_08510
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle External Knowledge Injection for CLIP-Based Class-Incremental Learning
Zhou, Da-Wei
Li, Kai-Wen
Ning, Jingyi
Ye, Han-Jia
Zhang, Lijun
Zhan, De-Chuan
Computer Vision and Pattern Recognition
Machine Learning
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
title External Knowledge Injection for CLIP-Based Class-Incremental Learning
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.08510