English
Related papers

Related papers: What do we learn from inverting CLIP models?

200 papers

CLIP has emerged as a powerful multimodal model capable of connecting images and text through joint embeddings, but to what extent does it 'see' the same way humans do - especially when interpreting artworks? In this paper, we investigate…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Andrea Asperti , Leonardo Dessì , Maria Chiara Tonetti , Nico Wu

We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "meta-instructions" that control how models answer users'…

Cryptography and Security · Computer Science 2025-06-16 Tingwei Zhang , Collin Zhang , John X. Morris , Eugene Bagdasarian , Vitaly Shmatikov

Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks. It is usually expected that satisfactory overall accuracy…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Jie-Jing Shao , Jiang-Xin Shi , Xiao-Wen Yang , Lan-Zhe Guo , Yu-Feng Li

Large-scale Vision-Language Models, such as CLIP, learn powerful image-text representations that have found numerous applications, from zero-shot classification to text-to-image generation. Despite that, their capabilities for solving novel…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Aleksandar Shtedritski , Christian Rupprecht , Andrea Vedaldi

Contrastive Language-Image Pre-training (CLIP) has become a foundation model and has been applied to various vision and multimodal tasks. However, recent works indicate that CLIP falls short in distinguishing detailed differences in images…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Yinqi Li , Jiahe Zhao , Hong Chang , Ruibing Hou , Shiguang Shan , Xilin Chen

In cinema, visual motifs are recurrent iconographic compositions that carry artistic or aesthetic significance. Their use throughout the history of visual arts and media is interesting to researchers and filmmakers alike. Our goal in this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Adam Phillips , Daniel Grandes Rodriguez , Miriam Sánchez-Manzano , Alan Salvadó , Manuel Garin , Gloria Haro , Coloma Ballester

We explore the oscillatory behavior observed in inversion methods applied to large-scale text-to-image diffusion models, with a focus on the "Flux" model. By employing a fixed-point-inspired iterative approach to invert real-world images,…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Yan Zheng , Zhenxiao Liang , Xiaoyan Cong , Lanqing guo , Yuehao Wang , Peihao Wang , Zhangyang Wang

Contrastive Language-Image Pre-training (CLIP) achieves remarkable performance in various downstream tasks through the alignment of image and text input embeddings and holds great promise for anomaly detection. However, our empirical…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Adam Goodge , Bryan Hooi , Wee Siong Ng

Pre-trained vision-language models such as CLIP exhibit strong transferability, yet adapting them to downstream image classification tasks under limited annotation budgets remains challenging. In active learning settings, the model must…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Qian-Wei Wang , Yaguang Song , Shu-Tao Xia

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

CLIP models learn transferable multi-modal features via image-text contrastive learning on internet-scale data. They are widely used in zero-shot classification, multi-modal retrieval, text-to-image diffusion, and as image encoders in large…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Marc-Antoine Lavoie , Anas Mahmoud , Aldo Zaimi , Arsene Fansi Tchango , Steven L. Waslander

Understanding verbs is crucial to modelling how people and objects interact with each other and the environment through space and time. Recently, state-of-the-art video-language models based on CLIP have been shown to have limited verb…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Liliane Momeni , Mathilde Caron , Arsha Nagrani , Andrew Zisserman , Cordelia Schmid

Improper exposure often leads to severe loss of details, color distortion, and reduced contrast. Exposure correction still faces two critical challenges: (1) the ignorance of object-wise regional semantic information causes the color shift…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Puzhen Wu , Han Weng , Quan Zheng , Yi Zhan , Hewei Wang , Yiming Li , Jiahui Han , Rui Xu

Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption. Given that recent…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Alberto Baldrati , Marco Bertini , Tiberio Uricchio , Alberto del Bimbo

Photo search, the task of retrieving images based on textual queries, has witnessed significant advancements with the introduction of CLIP (Contrastive Language-Image Pretraining) model. CLIP leverages a vision-language pre training…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Naresh Kumar Lahajal , Harini S

Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training paradigm, successfully introduces text supervision to vision models. It has shown promising results across various tasks due to its generalizability and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Zihao Zhao , Yuxiao Liu , Han Wu , Mei Wang , Yonghao Li , Sheng Wang , Lin Teng , Disheng Liu , Zhiming Cui , Qian Wang , Dinggang Shen

A pre-trained visual-language model, contrastive language-image pre-training (CLIP), successfully accomplishes various downstream tasks with text prompts, such as finding images or localizing regions within the image. Despite CLIP's strong…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 YeongHyeon Park , Myung Jin Kim , Hyeong Seok Kim

In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pairs as negatives. This approach has led to remarkable outcomes…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Maxwell Aladago , Lorenzo Torresani , Soroush Vosoughi

Image-to-image translation is affected by entanglement phenomena, which may occur in case of target data encompassing occlusions such as raindrops, dirt, etc. Our unsupervised model-based learning disentangles scene and occlusions, while…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Fabio Pizzati , Pietro Cerri , Raoul de Charette

The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Roni Paiss , Hila Chefer , Lior Wolf