English
Related papers

Related papers: Explaining and Mitigating the Modality Gap in Cont…

200 papers

Contrastive Language-Image Pretraining (CLIP) models excel at understanding image-text relationships but struggle with adapting to new data without forgetting prior knowledge. To address this, models are typically fine-tuned using both new…

Machine Learning · Computer Science 2026-05-06 Ryan King , Gang Li , Bobak Mortazavi , Tianbao Yang

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

Multimodal multilabel classification (MMC) is a challenging task that aims to design a learning algorithm to handle two data sources, the image and text, and learn a comprehensive semantic feature presentation across the modalities. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Yanming Guo

Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-25 Sachin Mehta , Maxwell Horton , Fartash Faghri , Mohammad Hossein Sekhavat , Mahyar Najibi , Mehrdad Farajtabar , Oncel Tuzel , Mohammad Rastegari

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

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Hiroshi Sasaki

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 François Role , Sébastien Meyer , Victor Amblard

Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in vision-language representation learning, powering diverse downstream tasks and serving as the default vision backbone in multimodal large language models (MLLMs).…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Chuan Qin , Constantin Venhoff , Sonia Joseph , Fanyi Xiao , Stefan Scherer

Contrastive language-image pre-training (CLIP) serves as a de-facto standard to align images and texts. Nonetheless, the loose correlation between images and texts of web-crawled data renders the contrastive objective data inefficient and…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Jinghao Zhou , Li Dong , Zhe Gan , Lijuan Wang , Furu Wei

The success of vision-language models is primarily attributed to effective alignment across modalities such as vision and language. However, modality gaps persist in existing alignment algorithms and appear necessary for human perception as…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Hanqi Yan , Xiangxiang Cui , Lu Yin , Jindong Gu , Paul Pu Liang , Yulan He , Yifei Wang

Understanding dark scenes based on multi-modal image data is challenging, as both the visible and auxiliary modalities provide limited semantic information for the task. Previous methods focus on fusing the two modalities but neglect the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-22 Xiaoyu Dong , Naoto Yokoya

The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Tiancheng Gu , Kaicheng Yang , Ziyong Feng , Xingjun Wang , Yanzhao Zhang , Dingkun Long , Yingda Chen , Weidong Cai , Jiankang Deng

Training models to apply common-sense linguistic knowledge and visual concepts from 2D images to 3D scene understanding is a promising direction that researchers have only recently started to explore. However, it still remains understudied…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Alexandros Delitzas , Maria Parelli , Nikolas Hars , Georgios Vlassis , Sotirios Anagnostidis , Gregor Bachmann , Thomas Hofmann

Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical results, InfoNCE-based objectives introduce inherent conflicts that yield…

Machine Learning · Computer Science 2026-02-11 Wenzhe Yin , Pan Zhou , Zehao Xiao , Jie Liu , Shujian Yu , Jan-Jakob Sonke , Efstratios Gavves

The Contrastive Language-Image Pre-training (CLIP) Model is a recently proposed large-scale pre-train model which attracts increasing attention in the computer vision community. Benefiting from its gigantic image-text training set, the CLIP…

Computer Vision and Pattern Recognition · Computer Science 2022-07-21 Yuxuan Ding , Lingqiao Liu , Chunna Tian , Jingyuan Yang , Haoxuan Ding

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success in cross-modal tasks such as zero-shot image classification and text-image retrieval by effectively aligning visual and textual representations. However, the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Yingrui Ji , Xi Xiao , Gaofei Chen , Hao Xu , Chenrui Ma , Lijing Zhu , Aokun Liang , Jiansheng Chen

Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…

Machine Learning · Statistics 2025-06-02 Ricardo Baptista , Andrew M. Stuart , Son Tran

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

Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream task. In this paper, we approach the document classification problem…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Souhail Bakkali , Zuheng Ming , Mickael Coustaty , Marçal Rusiñol , Oriol Ramos Terrades

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Fawaz Sammani , Nikos Deligiannis