English
Related papers

Related papers: The Hard Positive Truth about Vision-Language Comp…

200 papers

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

Contrastive Language-Image Pre-training (CLIP) on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. However, such models require a massive amount of pre-training data. Improving…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Siddharth Joshi , Arnav Jain , Ali Payani , Baharan Mirzasoleiman

In this paper, we propose a new method to enhance compositional understanding in pre-trained vision and language models (VLMs) without sacrificing performance in zero-shot multi-modal tasks. Traditional fine-tuning approaches often improve…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Youngtaek Oh , Jae Won Cho , Dong-Jin Kim , In So Kweon , Junmo Kim

Existing vision-text contrastive learning like CLIP aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction. However, medical…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Zifeng Wang , Zhenbang Wu , Dinesh Agarwal , Jimeng Sun

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

Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Enrico Fini , Pietro Astolfi , Adriana Romero-Soriano , Jakob Verbeek , Michal Drozdzal

Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Yassine Ouali , Adrian Bulat , Alexandros Xenos , Anestis Zaganidis , Ioannis Maniadis Metaxas , Brais Martinez , Georgios Tzimiropoulos

The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new recipe for a…

Computer Vision and Pattern Recognition · Computer Science 2023-07-21 Sara Sarto , Manuele Barraco , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

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

Contrastive Language-Image Pre-training (CLIP)~\citep{radford2021learning} has emerged as a pivotal model in computer vision and multimodal learning, achieving state-of-the-art performance at aligning visual and textual representations…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Shaoan Xie , Lingjing Kong , Yujia Zheng , Yu Yao , Zeyu Tang , Eric P. Xing , Guangyi Chen , Kun Zhang

Vision-language models (VLMs) such as CLIP are trained via contrastive learning between text and image pairs, resulting in aligned image and text embeddings that are useful for many downstream tasks. A notable drawback of CLIP, however, is…

Machine Learning · Computer Science 2025-07-08 Dylan Sam , Devin Willmott , Joao D. Semedo , J. Zico Kolter

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

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Samuel Lavoie , Polina Kirichenko , Mark Ibrahim , Mahmoud Assran , Andrew Gordon Wilson , Aaron Courville , Nicolas Ballas

Contrastive Language-Image Pre-training (CLIP) formulates image classification as an image-to-text matching task, i.e., matching images to the corresponding natural language descriptions instead of discrete category IDs. This allows for…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Shuhuai Ren , Lei Li , Xuancheng Ren , Guangxiang Zhao , Xu Sun

CLIP models perform remarkably well on zero-shot classification and retrieval tasks. But recent studies have shown that learnt representations in CLIP are not well suited for dense prediction tasks like object detection, semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Pavan Kumar Anasosalu Vasu , Hadi Pouransari , Fartash Faghri , Oncel Tuzel

Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Beichen Zhang , Pan Zhang , Xiaoyi Dong , Yuhang Zang , Jiaqi Wang

During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Yuting Gao , Jinfeng Liu , Zihan Xu , Tong Wu Enwei Zhang , Wei Liu , Jie Yang , Ke Li , Xing Sun

Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Chenyu You , Yifei Min , Weicheng Dai , Jasjeet S. Sekhon , Lawrence Staib , James S. Duncan

Joint vision-language models have shown great performance over a diverse set of tasks. However, little is known about their limitations, as the high dimensional space learned by these models makes it difficult to identify semantic errors.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Santiago Castro , Oana Ignat , Rada Mihalcea

Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…

Computer Vision and Pattern Recognition · Computer Science 2023-08-11 Longtian Qiu , Renrui Zhang , Ziyu Guo , Ziyao Zeng , Zilu Guo , Yafeng Li , Guangnan Zhang