English
Related papers

Related papers: TaCA: Upgrading Your Visual Foundation Model with …

200 papers

This study aims to explore efficient tuning methods for the screenshot captioning task. Recently, image captioning has seen significant advancements, but research in captioning tasks for mobile screens remains relatively scarce. Current…

Machine Learning · Computer Science 2023-09-27 Ching-Yu Chiang , I-Hua Chang , Shih-Wei Liao

Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Victor Akinwande , Mohammad Sadegh Norouzzadeh , Devin Willmott , Anna Bair , Madan Ravi Ganesh , J. Zico Kolter

So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules. However, existing methods overlook a crucial issue: if the underlying…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Zhengbo Wang , Jian Liang , Lijun Sheng , Ran He , Zilei Wang , Tieniu Tan

Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Existing pre-trained model-based CIL methods often freeze the pre-trained network and adapt to incremental tasks using…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Yan Wang , Da-Wei Zhou , Han-Jia Ye

Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods, such as prompt learning and adapter, to enhance CLIP's…

Computer Vision and Pattern Recognition · Computer Science 2024-02-07 Zhengbo Wang , Jian Liang , Lijun Sheng , Ran He , Zilei Wang , Tieniu Tan

This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-30 Junyang Wu , Xianhang Li , Chen Wei , Huiyu Wang , Alan Yuille , Yuyin Zhou , Cihang Xie

Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test…

Machine Learning · Computer Science 2025-06-10 Linjing You , Jiabao Lu , Xiayuan Huang

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Haotian Liu , Kilho Son , Jianwei Yang , Ce Liu , Jianfeng Gao , Yong Jae Lee , Chunyuan Li

Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transformer-based encoders…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Pavan Kumar Anasosalu Vasu , Hadi Pouransari , Fartash Faghri , Raviteja Vemulapalli , Oncel Tuzel

Recently, large-scale pre-trained vision-language models (e.g. CLIP and ALIGN) have demonstrated remarkable effectiveness in acquiring transferable visual representations. To leverage the valuable knowledge encoded within these models for…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Yi Zhang , Ce Zhang , Xueting Hu , Zhihai He

In the big data era, the computer vision field benefits from large-scale datasets such as LAION-2B, LAION-400M, and ImageNet-21K, Kinetics, on which popular models like the ViT and ConvNeXt series have been pre-trained, acquiring…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Qiankun Li , Feng He , Huabao Chen , Xin Ning , Kun Wang , Zengfu Wang

Pre-trained Vision-Language (V-L) models set the benchmark for generalization to downstream tasks among the noteworthy contenders. Many characteristics of the V-L model have been explored in existing research including the challenge of the…

Computer Vision and Pattern Recognition · Computer Science 2024-01-24 Guiming Cao , Kaize Shi , Hong Fu , Huaiwen Zhang , Guandong Xu

Few-shot learning (FSL) often requires effective adaptation of models using limited labeled data. However, most existing FSL methods rely on entangled representations, requiring the model to implicitly recover the unmixing process to obtain…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Tianjiao Jiang , Zhen Zhang , Yuhang Liu , Javen Qinfeng Shi

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Chenyang Zhao , Kun Wang , Janet H. Hsiao , Antoni B. Chan

Vision-language models (VLMs) like CLIP have demonstrated remarkable applicability across a variety of downstream tasks, including zero-shot image classification. Recently, the use of prompts or adapters for efficient transfer learning…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Yongjin Yang , Jongwoo Ko , Se-Young Yun

Pre-trained vision-language models like CLIP have shown powerful zero-shot inference ability via image-text matching and prove to be strong few-shot learners in various downstream tasks. However, in real-world scenarios, adapting CLIP to…

Computer Vision and Pattern Recognition · Computer Science 2024-06-19 Jiang-Xin Shi , Chi Zhang , Tong Wei , Yu-Feng Li

Recent advancements in pre-trained vision-language models like CLIP have enabled the task of open-vocabulary segmentation. CLIP demonstrates impressive zero-shot capabilities in various downstream tasks that require holistic image…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Sule Bai , Yong Liu , Yifei Han , Haoji Zhang , Yansong Tang , Jie Zhou , Jiwen Lu

Multi-task ``vision-language-action'' (VLA) models have recently demonstrated increasing promise as generalist foundation models for robotics, achieving non-trivial performance out of the box on new tasks in new environments. However, for…

Robotics · Computer Science 2025-08-05 Kaustubh Sridhar , Souradeep Dutta , Dinesh Jayaraman , Insup Lee

Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and test data. Recent works have focused on backpropagation-free TTA methods that rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Zhaohong Huang , Yuxin Zhang , Wenjing Liu , Fei Chao , Rongrong Ji

Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning.…

Cryptography and Security · Computer Science 2025-09-15 Hondamunige Prasanna Silva , Federico Becattini , Lorenzo Seidenari