English
Related papers

Related papers: Text encoders bottleneck compositionality in contr…

200 papers

CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP's language supervision or its much larger training data. To disentangle…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Yiming Liu , Yuhui Zhang , Dhruba Ghosh , Ludwig Schmidt , Serena Yeung-Levy

Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Do Huu Dat , Nam Hyeonu , Po-Yuan Mao , Tae-Hyun Oh

Context Optimization (CoOp) has emerged as a simple yet effective technique for adapting CLIP-like vision-language models to downstream image recognition tasks. Nevertheless, learning compact context with satisfactory base-to-new, domain…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Kun Ding , Xiaohui Li , Qiang Yu , Ying Wang , Haojian Zhang , Shiming Xiang

Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an…

Large-scale neural network models combining text and images have made incredible progress in recent years. However, it remains an open question to what extent such models encode compositional representations of the concepts over which they…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Martha Lewis , Nihal V. Nayak , Peilin Yu , Qinan Yu , Jack Merullo , Stephen H. Bach , Ellie Pavlick

Video-text retrieval plays an essential role in multi-modal research and has been widely used in many real-world web applications. The CLIP (Contrastive Language-Image Pre-training), an image-language pre-training model, has demonstrated…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Huaishao Luo , Lei Ji , Ming Zhong , Yang Chen , Wen Lei , Nan Duan , Tianrui Li

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent compositional concepts effectively. These works suggest that CLIP often…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Darina Koishigarina , Arnas Uselis , Seong Joon Oh

Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality causes large drops in accuracy and severe miscalibration, and the model does not behave…

Computation and Language · Computer Science 2026-05-14 Mingyeong Kim , Jungwon Choi , Chaeyun Jang , Juho Lee

Contrastive Language-Image Pre-training (CLIP) models excel in zero-shot classification, yet face challenges in complex multi-object scenarios. This study offers a comprehensive analysis of CLIP's limitations in these contexts using a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Reza Abbasi , Ali Nazari , Aminreza Sefid , Mohammadali Banayeeanzade , Mohammad Hossein Rohban , Mahdieh Soleymani Baghshah

Multilingual vision-language models exhibit systematic performance gaps across languages, but the mechanism remains ambiguous: cross-language divergence could arise from the visual encoder, the text branch, or their interaction. We resolve…

Computation and Language · Computer Science 2026-05-12 J. de Curtò , Mauro Liz , I. de Zarzà

Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image caption as a "bag of words". As a result, they perform poorly on…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Fiorenzo Parascandolo , Nicholas Moratelli , Enver Sangineto , Lorenzo Baraldi , Rita Cucchiara

Conventional object detectors rely on cross-entropy classification, which can be vulnerable to class imbalance and label noise. We propose CLIP-Joint-Detect, a simple and detector-agnostic framework that integrates CLIP-style contrastive…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Behnam Raoufi , Hossein Sharify , Mohamad Mahdee Ramezanee , Khosrow Hajsadeghi , Saeed Bagheri Shouraki

Despite the success of large-scale pretrained Vision-Language Models (VLMs) especially CLIP in various open-vocabulary tasks, their application to semantic segmentation remains challenging, producing noisy segmentation maps with…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Mengcheng Lan , Chaofeng Chen , Yiping Ke , Xinjiang Wang , Litong Feng , Wayne Zhang

We investigate 17 benchmarks (e.g. SugarCREPE, VALSE) commonly used for measuring compositional understanding capabilities of vision-language models (VLMs). We scrutinize design choices in their construction, including data source (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Vishaal Udandarao , Mehdi Cherti , Shyamgopal Karthik , Jenia Jitsev , Samuel Albanie , Matthias Bethge

In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Chaorui Deng , Qi Chen , Pengda Qin , Da Chen , Qi Wu

Contrastive Language-Image Pretraining (CLIP) efficiently learns visual concepts by pre-training with natural language supervision. CLIP and its visual encoder have been explored on various vision and language tasks and achieve strong…

Computation and Language · Computer Science 2022-10-13 An Yan , Jiacheng Li , Wanrong Zhu , Yujie Lu , William Yang Wang , Julian McAuley

Contrastive vision-language models like CLIP have achieved impressive results in image-text retrieval by aligning image and text representations in a shared embedding space. However, these models often treat text as flat sequences, limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Ruijia Wu , Ping Chen , Fei Shen , Shaoan Zhao , Qiang Hui , Huanlin Gao , Ting Lu , Zhaoxiang Liu , Fang Zhao , Kai Wang , Shiguo Lian

Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world. However, it has been observed that…

Computer Vision and Pattern Recognition · Computer Science 2021-07-15 Sheng Shen , Liunian Harold Li , Hao Tan , Mohit Bansal , Anna Rohrbach , Kai-Wei Chang , Zhewei Yao , Kurt Keutzer

Chart understanding requires models to effectively analyze and reason about numerical data, textual elements, and complex visual components. Our observations reveal that the perception capabilities of existing large vision-language models…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Junteng Liu , Weihao Zeng , Xiwen Zhang , Yijun Wang , Zifei Shan , Junxian He

Contrastive Language-Image Pretraining (CLIP) has demonstrated strong generalization for vision-language tasks in computer vision and medical domains, yet its text encoder accepts only up to 77 tokens, which limits its ability to represent…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Xiaoyang Wei , Camille Kurtz , Florence Cloppet
‹ Prev 1 4 5 6 7 8 10 Next ›