English
Related papers

Related papers: Enhancing CLIP Robustness via Cross-Modality Align…

200 papers

Pre-trained vision-language models (VLMs) such as CLIP have demonstrated strong zero-shot capabilities across diverse domains, yet remain highly vulnerable to adversarial perturbations that disrupt image-text alignment and compromise…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Jiaxiang Liu , Jiawei Du , Xiao Liu , Prayag Tiwari , Mingkun Xu

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Lijie Zhou

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on…

Computer Vision and Pattern Recognition · Computer Science 2024-11-13 Wanqi Zhou , Shuanghao Bai , Danilo P. Mandic , Qibin Zhao , Badong Chen

The robustness of Vision-Language Models (VLMs) such as CLIP is critical for their deployment in safety-critical applications like autonomous driving, healthcare diagnostics, and security systems, where accurate interpretation of visual and…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Yuhan Liang , Yijun Li , Yumeng Niu , Qianhe Shen , Hangyu Liu

Multi-modal foundation models like OpenFlamingo, LLaVA, and GPT-4 are increasingly used for various real-world tasks. Prior work has shown that these models are highly vulnerable to adversarial attacks on the vision modality. These attacks…

Machine Learning · Computer Science 2024-06-06 Christian Schlarmann , Naman Deep Singh , Francesco Croce , Matthias Hein

Vision-language models (VLMs), such as CLIP, have demonstrated exceptional generalization capabilities and can quickly adapt to downstream tasks through prompt fine-tuning. Unfortunately, in classification tasks involving non-training…

Computer Vision and Pattern Recognition · Computer Science 2025-02-06 Song-Lin Lv , Yu-Yang Chen , Zhi Zhou , Yu-Feng Li , Lan-Zhe Guo

Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent studies propose to finetune the vision encoder of CLIP with…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Songlong Xing , Zhengyu Zhao , Nicu Sebe

Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Le Zhang , Rabiul Awal , Aishwarya Agrawal

Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for a variety of applications. In this paper, we show that the common practice of individually exploiting the text or image encoders of these powerful…

Computer Vision and Pattern Recognition · Computer Science 2025-02-07 Marco Mistretta , Alberto Baldrati , Lorenzo Agnolucci , Marco Bertini , Andrew D. Bagdanov

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Jiaxiang Liu , Yuan Wang , Jiawei Du , Joey Tianyi Zhou , Mingkun Xu , Zuozhu Liu

Contrastive Language-Image Pre-training (CLIP) models have shown significant potential, particularly in zero-shot classification across diverse distribution shifts. Building on existing evaluations of overall classification robustness, this…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Weijie Tu , Weijian Deng , Tom Gedeon

Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Md Zarif Hossain , Ahmed Imteaj

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

Contrastive language image pre-training (CLIP) is an essential component of building modern vision-language foundation models. While CLIP demonstrates remarkable zero-shot performance on downstream tasks, the multi-modal feature spaces…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Shin'ya Yamaguchi , Dewei Feng , Sekitoshi Kanai , Kazuki Adachi , Daiki Chijiwa

Deep Learning (DL) is undergoing a paradigm shift with the emergence of foundation models. In this work, we focus on Contrastive Language-Image Pre-training (CLIP), a Vision-Language foundation model that achieves high accuracy across…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Angelos Zavras , Dimitrios Michail , Begüm Demir , Ioannis Papoutsis

Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the modality gap. This gap limits tasks requiring cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Hongyuan Liu , Qinli Yang , Wen Li , Zhong Zhang , Jiaming Liu , Wei Han , Zhili Qin , Jinxia Guo , Junming Shao

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

Computer Vision and Pattern Recognition · Computer Science 2022-04-12 Alex Andonian , Shixing Chen , Raffay Hamid

Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Beier Zhu , Kaihua Tang , Qianru Sun , Hanwang Zhang

This paper investigates the robustness of vision-language models against adversarial visual perturbations and introduces a novel ``double visual defense" to enhance this robustness. Unlike previous approaches that resort to lightweight…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Zeyu Wang , Cihang Xie , Brian Bartoldson , Bhavya Kailkhura

Pretrained large-scale vision-language models like CLIP have exhibited strong generalization over unseen tasks. Yet imperceptible adversarial perturbations can significantly reduce CLIP's performance on new tasks. In this work, we identify…

Computer Vision and Pattern Recognition · Computer Science 2023-04-24 Chengzhi Mao , Scott Geng , Junfeng Yang , Xin Wang , Carl Vondrick
‹ Prev 1 2 3 10 Next ›