English
Related papers

Related papers: Understanding the Robustness of Multi-modal Contra…

200 papers

CLIP models learn transferable multi-modal features via image-text contrastive learning on internet-scale data. They are widely used in zero-shot classification, multi-modal retrieval, text-to-image diffusion, and as image encoders in large…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Marc-Antoine Lavoie , Anas Mahmoud , Aldo Zaimi , Arsene Fansi Tchango , Steven L. Waslander

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

We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and text) are embedded at arm's length in their shared…

Computation and Language · Computer Science 2022-10-21 Weixin Liang , Yuhui Zhang , Yongchan Kwon , Serena Yeung , James Zou

Advancements in technologies related to working with omics data require novel computation methods to fully leverage information and help develop a better understanding of human diseases. This paper studies the effects of introducing graph…

Genomics · Quantitative Biology 2023-10-17 Nishant Rajadhyaksha , Aarushi Chitkara

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…

Most multi-view clustering methods are limited by shallow models without sound nonlinear information perception capability, or fail to effectively exploit complementary information hidden in different views. To tackle these issues, we…

Machine Learning · Computer Science 2022-10-14 Fu Lele , Zhang Lei , Yang Jinghua , Chen Chuan , Zhang Chuanfu , Zheng Zibin

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Xinyue Huo , Lingxi Xie , Longhui Wei , Xiaopeng Zhang , Hao Li , Zijie Yang , Wengang Zhou , Houqiang Li , Qi Tian

Cross-modal retrieval is the task of retrieving samples of a given modality by using queries of a different one. Due to the wide range of practical applications, the problem has been mainly focused on the vision and language case, e.g. text…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Jorge Sánchez , Rodrigo Laguna

Deep Image Manipulation Localization (IML) models suffer from training data insufficiency and thus heavily rely on pre-training. We argue that contrastive learning is more suitable to tackle the data insufficiency problem for IML. Crafting…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Jizhe Zhou , Xiaochen Ma , Xia Du , Ahmed Y. Alhammadi , Wentao Feng

In a wide range of multimodal tasks, contrastive learning has become a particularly appealing approach since it can successfully learn representations from abundant unlabeled data with only pairing information (e.g., image-caption or…

Machine Learning · Computer Science 2023-10-31 Paul Pu Liang , Zihao Deng , Martin Ma , James Zou , Louis-Philippe Morency , Ruslan Salakhutdinov

Deep multimodal learning has shown remarkable success by leveraging contrastive learning to capture explicit one-to-one relations across modalities. However, real-world data often exhibits shared relations beyond simple pairwise…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Raja Kumar , Raghav Singhal , Pranamya Kulkarni , Deval Mehta , Kshitij Jadhav

Pre-trained multi-modal models, such as CLIP, provide transferable embeddings and show promising results in diverse applications. However, the analysis of learned multi-modal embeddings is relatively unexplored, and the embedding…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Changdae Oh , Junhyuk So , Hoyoon Byun , YongTaek Lim , Minchul Shin , Jong-June Jeon , Kyungwoo Song

Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transformer-based encoders…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Pavan Kumar Anasosalu Vasu , Hadi Pouransari , Fartash Faghri , Raviteja Vemulapalli , Oncel Tuzel

Given a similarity metric, contrastive methods learn a representation in which examples that are similar are pushed together and examples that are dissimilar are pulled apart. Contrastive learning techniques have been utilized extensively…

Machine Learning · Computer Science 2023-07-07 Emily Mu , John Guttag , Maggie Makar

As multimodal learning finds applications in a wide variety of high-stakes societal tasks, investigating their robustness becomes important. Existing work has focused on understanding the robustness of vision-and-language models to…

Machine Learning · Computer Science 2022-11-07 Gaurav Verma , Vishwa Vinay , Ryan A. Rossi , Srijan Kumar

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

Machine Learning · Computer Science 2023-08-16 Huangjie Zheng , Xu Chen , Jiangchao Yao , Hongxia Yang , Chunyuan Li , Ya Zhang , Hao Zhang , Ivor Tsang , Jingren Zhou , Mingyuan Zhou

The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generalize to an entirely…

Machine Learning · Computer Science 2025-09-15 Elias Kempf , Simon Schrodi , Max Argus , Thomas Brox

Self-Supervised Learning (SSL) is a paradigm that leverages unlabeled data for model training. Empirical studies show that SSL can achieve promising performance in distribution shift scenarios, where the downstream and training…

Machine Learning · Computer Science 2023-12-13 Xuyang Zhao , Tianqi Du , Yisen Wang , Jun Yao , Weiran Huang

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
‹ Prev 1 4 5 6 7 8 10 Next ›