{"title":"Learning with Enriched Inductive Biases for Vision-Language Models","authors":"Lingxiao Yang, Ru-Yuan Zhang, Qi Chen, Xiaohua Xie","doi":"10.1007/s11263-025-02354-1","DOIUrl":null,"url":null,"abstract":"<p>Vision-Language Models, pre-trained on large-scale image-text pairs, serve as strong foundation models for transfer learning across a variety of downstream tasks. For few-shot generalization tasks, <i>i.e</i>., when the model is trained on few-shot samples and then tested on unseen categories or datasets, there is a balance to be struck between generalization and discrimination when tweaking these models. Existing approaches typically rely on one or two strategies during training to learn task-specific knowledge, while preserving as much task-agnostic representation as possible. However, these methods overlook the importance of other useful inductive biases, thereby limiting their generalization capabilities. In this work, we propose a method – <b>L</b>earning <b>w</b>ith <b>E</b>nriched <b>I</b>nductive <b>B</b>iases (LwEIB) – to explore multiple inductive biases at the text, model, and optimization levels. Specifically, we first propose to enrich the handcrafted text prompt with Large Language Model generated descriptions for each category. To better capture structural cues in both linguistics and vision, we design two new adapters for text and image encoders, respectively. Additionally, we propose a slow-fast optimization method to explore different degrees of adaptation more efficiently, learning task-specific representations while maintaining task-agnostic ones. We empirically validate the effectiveness of LwEIB on three widely used benchmarks. Remarkably, our LwEIB outperforms numerous state-of-the-art methods across all evaluation metrics, demonstrating its efficacy and versatility. Our code is available at https://github.com/ZjjConan/VLM-LwEIB.</p>","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":"59 1","pages":""},"PeriodicalIF":11.6000,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Computer Vision","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11263-025-02354-1","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Vision-Language Models, pre-trained on large-scale image-text pairs, serve as strong foundation models for transfer learning across a variety of downstream tasks. For few-shot generalization tasks, i.e., when the model is trained on few-shot samples and then tested on unseen categories or datasets, there is a balance to be struck between generalization and discrimination when tweaking these models. Existing approaches typically rely on one or two strategies during training to learn task-specific knowledge, while preserving as much task-agnostic representation as possible. However, these methods overlook the importance of other useful inductive biases, thereby limiting their generalization capabilities. In this work, we propose a method – Learning with Enriched Inductive Biases (LwEIB) – to explore multiple inductive biases at the text, model, and optimization levels. Specifically, we first propose to enrich the handcrafted text prompt with Large Language Model generated descriptions for each category. To better capture structural cues in both linguistics and vision, we design two new adapters for text and image encoders, respectively. Additionally, we propose a slow-fast optimization method to explore different degrees of adaptation more efficiently, learning task-specific representations while maintaining task-agnostic ones. We empirically validate the effectiveness of LwEIB on three widely used benchmarks. Remarkably, our LwEIB outperforms numerous state-of-the-art methods across all evaluation metrics, demonstrating its efficacy and versatility. Our code is available at https://github.com/ZjjConan/VLM-LwEIB.
期刊介绍:
The International Journal of Computer Vision (IJCV) serves as a platform for sharing new research findings in the rapidly growing field of computer vision. It publishes 12 issues annually and presents high-quality, original contributions to the science and engineering of computer vision. The journal encompasses various types of articles to cater to different research outputs.
Regular articles, which span up to 25 journal pages, focus on significant technical advancements that are of broad interest to the field. These articles showcase substantial progress in computer vision.
Short articles, limited to 10 pages, offer a swift publication path for novel research outcomes. They provide a quicker means for sharing new findings with the computer vision community.
Survey articles, comprising up to 30 pages, offer critical evaluations of the current state of the art in computer vision or offer tutorial presentations of relevant topics. These articles provide comprehensive and insightful overviews of specific subject areas.
In addition to technical articles, the journal also includes book reviews, position papers, and editorials by prominent scientific figures. These contributions serve to complement the technical content and provide valuable perspectives.
The journal encourages authors to include supplementary material online, such as images, video sequences, data sets, and software. This additional material enhances the understanding and reproducibility of the published research.
Overall, the International Journal of Computer Vision is a comprehensive publication that caters to researchers in this rapidly growing field. It covers a range of article types, offers additional online resources, and facilitates the dissemination of impactful research.