English
Related papers

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

200 papers

Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the training data a significant factor in the efficacy of CLIP for…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Maitreya Patel , Abhiram Kusumba , Sheng Cheng , Changhoon Kim , Tejas Gokhale , Chitta Baral , Yezhou Yang

Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Austin Stone , Hagen Soltau , Robert Geirhos , Xi Yi , Ye Xia , Bingyi Cao , Kaifeng Chen , Abhijit Ogale , Jonathon Shlens

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

Vision-language models like CLIP have demonstrated remarkable zero-shot capabilities in classification and retrieval. However, these models often struggle with compositional reasoning - the ability to understand the relationships between…

Machine Learning · Computer Science 2025-10-29 Amit Peleg , Naman Deep Singh , Matthias Hein

Contrastive Language-Image Pre-training (CLIP) delivers strong cross modal generalization by aligning images and texts in a shared embedding space, yet it persistently fails at compositional reasoning over objects, attributes, and relations…

Machine Learning · Computer Science 2025-10-31 Ziliang Chen , Tianang Xiao , Jusheng Zhang , Yongsen Zheng , Xipeng Chen

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

A fundamental characteristic common to both human vision and natural language is their compositional nature. Yet, despite the performance gains contributed by large vision and language pretraining, we find that: across 7 architectures…

Computation and Language · Computer Science 2023-05-17 Zixian Ma , Jerry Hong , Mustafa Omer Gul , Mona Gandhi , Irena Gao , Ranjay Krishna

Contrastive Language-Image Pretraining (CLIP) has demonstrated great zero-shot performance for matching images and text. However, it is still challenging to adapt vision-lanaguage pretrained models like CLIP to compositional image and text…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Kenan Jiang , Xuehai He , Ruize Xu , Xin Eric Wang

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

Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, visual question answering, captioning, and more. However, the…

Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured relationships between visual and linguistic elements. This…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Jihoon Kwon , Kyle Min , Jy-yong Sohn

Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Weiheng Zhao , Zilong Huang , Jiashi Feng , Xinggang Wang

Contrastive vision-language (V&L) models remain a popular choice for various applications. However, several limitations have emerged, most notably the limited ability of V&L models to learn compositional representations. Prior methods often…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Hai X. Pham , David T. Hoffmann , Ricardo Guerrero , Brais Martinez

The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditional image-only methods. Our work studies this question…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Shibani Santurkar , Yann Dubois , Rohan Taori , Percy Liang , Tatsunori Hashimoto

Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Yufeng Cui , Lichen Zhao , Feng Liang , Yangguang Li , Jing Shao

Performant vision-language (VL) models like CLIP represent captions using a single vector. How much information about language is lost in this bottleneck? We first curate CompPrompts, a set of increasingly compositional image captions that…

Computation and Language · Computer Science 2023-10-31 Amita Kamath , Jack Hessel , Kai-Wei Chang

Existing vision-language models (VLMs) treat text descriptions as a unit, confusing individual concepts in a prompt and impairing visual semantic matching and reasoning. An important aspect of reasoning in logic and language is negations.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Jaisidh Singh , Ishaan Shrivastava , Mayank Vatsa , Richa Singh , Aparna Bharati

Large-scale but noisy image-text pair data have paved the way for the success of Contrastive Language-Image Pretraining (CLIP). As the foundation vision encoder, CLIP in turn serves as the cornerstone for most large vision-language models…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Zhixiang Wei , Guangting Wang , Xiaoxiao Ma , Ke Mei , Huaian Chen , Yi Jin , Fengyun Rao

Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative. Our work continues this effort, introducing two simple yet…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Yanqing Liu , Xianhang Li , Zeyu Wang , Bingchen Zhao , Cihang Xie

Despite the success of Vision-Language Models (VLMs) like CLIP in aligning vision and language, their proficiency in detailed, fine-grained visual comprehension remains a key challenge. We present CLIP-IN, a novel framework that bolsters…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ziteng Wang , Siqi Yang , Limeng Qiao , Lin Ma
‹ Prev 1 2 3 10 Next ›