English
Related papers

Related papers: Half-Truths Break Similarity-Based Retrieval

200 papers

Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Konstantin Schall , Kai Uwe Barthel , Nico Hezel , Klaus Jung

CLIP is one of the most popular foundation models and is heavily used for many vision-language tasks, yet little is known about its inner workings. As CLIP is increasingly deployed in real-world applications, it is becoming even more…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Avinash Madasu , Vasudev Lal , Phillip Howard

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

Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Zhiyue Liu , Jinyuan Liu , Fanrong Ma

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

Contrastive Language-Image Pre-Training (CLIP) is highly instrumental in machine learning applications within a large variety of domains. We investigate the geometry of this embedding, which is still not well understood. We examine the raw…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Meir Yossef Levi , Guy Gilboa

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 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

Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable performance in zero-shot classification tasks, yet their efficacy in handling complex multi-object scenarios remains challenging. This study presents a…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Reza Abbasi , Ali Nazari , Aminreza Sefid , Mohammadali Banayeeanzade , Mohammad Hossein Rohban , Mahdieh Soleymani Baghshah

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 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…

Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Chuanyang Jin

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

Although CLIP-like Visual Language Models provide a functional joint feature space for image and text, due to the limitation of the CILP-like model's image input size (e.g., 224), subtle details are lost in the feature representation if we…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Zilun Zhang , Cuifeng Shen , Yuan Shen , Xinyu Zhou , Huixin Xiong , Tiancheng Zhao , Jianwei Yin

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

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

This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets. We explore CLIP along three dimensions: data, architecture, and training strategies. With regards…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Zichao Li , Cihang Xie , Ekin Dogus Cubuk

In the recent years, the dual-encoder vision-language models (\eg CLIP) have achieved remarkable text-to-image retrieval performance. However, we discover that these models usually results in very different retrievals for a pair of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Jiacheng Cheng , Hijung Valentina Shin , Nuno Vasconcelos , Bryan Russell , Fabian Caba Heilbron

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

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