English
Related papers

Related papers: Color in Visual-Language Models: CLIP deficiencies

200 papers

Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias. Such bias causes CLIP models to `Parrot' the visual text embedded within images while disregarding the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-02 Yiqi Lin , Conghui He , Alex Jinpeng Wang , Bin Wang , Weijia Li , Mike Zheng Shou

We evaluate the state-of-the-art multimodal "visual semantic" model CLIP ("Contrastive Language Image Pretraining") for biases related to the marking of age, gender, and race or ethnicity. Given the option to label an image as "a photo of a…

Computer Vision and Pattern Recognition · Computer Science 2022-05-24 Robert Wolfe , Aylin Caliskan

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

Computer Vision and Pattern Recognition · Computer Science 2024-02-22 Ahmet Iscen , Mathilde Caron , Alireza Fathi , Cordelia Schmid

Contrastive Language-Image Pre-Training (CLIP) is a popular method for learning multimodal latent spaces with well-organized semantics. Despite its wide range of applications, CLIP's latent space is known to fail at handling complex…

Machine Learning · Computer Science 2026-03-17 Raphi Kang , Yue Song , Georgia Gkioxari , Pietro Perona

While the Contrastive Language-Image Pretraining(CLIP) model has achieved remarkable success in a variety of downstream vison language understanding tasks, enhancing its capability for fine-grained image-text alignment remains an active…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Yicheng Xiao , Yu Chen , Haoxuan Ma , Jiale Hong , Caorui Li , Lingxiang Wu , Haiyun Guo , Jinqiao Wang

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

Training models to apply linguistic knowledge and visual concepts from 2D images to 3D world understanding is a promising direction that researchers have only recently started to explore. In this work, we design a novel 3D pre-training…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Maria Parelli , Alexandros Delitzas , Nikolas Hars , Georgios Vlassis , Sotirios Anagnostidis , Gregor Bachmann , Thomas Hofmann

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Haoxian Ruan , Zhihua Xu , Zhijing Yang , Yongyi Lu , Jinghui Qin , Tianshui Chen

Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites. This paper further explores CLIP from the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Tiancheng Gu , Kaicheng Yang , Xiang An , Ziyong Feng , Dongnan Liu , Weidong Cai , Jiankang Deng

Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are…

Computer Vision and Pattern Recognition · Computer Science 2023-01-03 Siyuan Li , Li Sun , Qingli Li

Image captioning is a fundamental task in vision-language understanding, where the model predicts a textual informative caption to a given input image. In this paper, we present a simple approach to address this task. We use CLIP encoding…

Computer Vision and Pattern Recognition · Computer Science 2021-11-19 Ron Mokady , Amir Hertz , Amit H. Bermano

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive.…

Computer Vision and Pattern Recognition · Computer Science 2023-05-10 Liangliang Cao , Bowen Zhang , Chen Chen , Yinfei Yang , Xianzhi Du , Wencong Zhang , Zhiyun Lu , Yantao Zheng

Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such performance does not realize in tasks that require a finer-grained correspondence…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Yutaro Yamada , Yingtian Tang , Yoyo Zhang , Ilker Yildirim

Recent advances in vision language models (VLM) have been driven by contrastive models such as CLIP, which learn to associate visual information with their corresponding text descriptions. However, these models have limitations in…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Rim Assouel , Pietro Astolfi , Florian Bordes , Michal Drozdzal , Adriana Romero-Soriano

Recent years have witnessed a significant increase in the performance of Vision and Language tasks. Foundational Vision-Language Models (VLMs), such as CLIP, have been leveraged in multiple settings and demonstrated remarkable performance…

Computer Vision and Pattern Recognition · Computer Science 2024-03-04 Santiago Castro , Amir Ziai , Avneesh Saluja , Zhuoning Yuan , Rada Mihalcea

Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization…

While recent work has found that vision-language models trained under the Contrastive Language Image Pre-training (CLIP) framework contain intrinsic social biases, the extent to which different upstream pre-training features of the…

Artificial Intelligence · Computer Science 2025-06-11 Kshitish Ghate , Isaac Slaughter , Kyra Wilson , Mona Diab , Aylin Caliskan

Contrastive vision-language models like CLIP have shown great progress in transfer learning. In the inference stage, the proper text description, also known as prompt, needs to be carefully designed to correctly classify the given images.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Tony Huang , Jack Chu , Fangyun Wei

Contrastive vision-language models like CLIP are used for a large variety of applications, such as zero-shot classification or as vision encoder for multi-modal models. Despite their popularity, their representations show major limitations.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Bijay Gurung , David T. Hoffmann , Thomas Brox

Recent years have witnessed the fast development of large-scale pre-training frameworks that can extract multi-modal representations in a unified form and achieve promising performances when transferred to downstream tasks. Nevertheless,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Xuran Pan , Tianzhu Ye , Dongchen Han , Shiji Song , Gao Huang