English
Related papers

Related papers: Is the Modality Gap a Bug or a Feature? A Robustne…

200 papers

Current vision language models face hallucination and robustness issues against ambiguous or corrupted modalities. We hypothesize that these issues can be addressed by exploiting the shared information between modalities to compensate for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yuriel Ryan , Hei Man Ip , Adriel Kuek , Paul Pu Liang , Roy Ka-Wei Lee

With the advent of vision-language models (VLMs) that can perform in-context and prompt-based learning, how can we design prompting approaches that robustly generalize to distribution shift and can be used on novel classes outside the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Jindong Gu , Ahmad Beirami , Xuezhi Wang , Alex Beutel , Philip Torr , Yao Qin

Large-scale multi-modal contrastive learning frameworks like CLIP typically require a large amount of image-text samples for training. However, these samples are always collected continuously in real scenarios. This paper discusses the…

Machine Learning · Computer Science 2023-06-02 Zixuan Ni , Longhui Wei , Siliang Tang , Yueting Zhuang , Qi Tian

Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Jingran Zhang , Fumin Shen , Xing Xu , Heng Tao Shen

Transfer learning enables the sharing of common knowledge among models for a variety of downstream tasks, but traditional methods suffer in limited training data settings and produce narrow models incapable of effectively generalizing under…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Kevin Vogt-Lowell , Noah Lee , Theodoros Tsiligkaridis , Marc Vaillant

The hubness problem widely exists in high-dimensional embedding space and is a fundamental source of error for cross-modal matching tasks. In this work, we study the emergence of hubs in Visual Semantic Embeddings (VSE) with application to…

Machine Learning · Computer Science 2019-11-25 Fangyu Liu , Rongtian Ye , Xun Wang , Shuaipeng Li

Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring which modalities each task actually requires. This…

Artificial Intelligence · Computer Science 2026-02-13 Nikhil Verma , Minjung Kim , JooYoung Yoo , Kyung-Min Jin , Manasa Bharadwaj , Kevin Ferreira , Ko Keun Kim , Youngjoon Kim

Utilizing a shared embedding space, emerging multimodal models exhibit unprecedented zero-shot capabilities. However, the shared embedding space could lead to new vulnerabilities if different modalities can be misaligned. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Shaeke Salman , Md Montasir Bin Shams , Xiuwen Liu

Multimodal co-embedding models, especially CLIP, have advanced the state of the art in zero-shot classification and multimedia information retrieval in recent years by aligning images and text in a shared representation space. However, such…

Multimedia · Computer Science 2025-11-10 Allie Tran , Luca Rossetto

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in…

Machine Learning · Statistics 2022-08-17 Xiaochen Yang , Yiwen Guo , Mingzhi Dong , Jing-Hao Xue

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

While Contrastive Language-Image Pretraining (CLIP) excels at zero-shot tasks by aligning image and text embeddings, its performance in few-shot classification is hindered by a critical limitation: intra-modal misalignment. This issue,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Christoph Timmermann , Hyunse Lee , Woojin Lee

Large-scale multimodal models have shown excellent performance over a series of tasks powered by the large corpus of paired multimodal training data. Generally, they are always assumed to receive modality-complete inputs. However, this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Lianyu Hu , Tongkai Shi , Wei Feng , Fanhua Shang , Liang Wan

By default neural networks are not robust to changes in data distribution. This has been demonstrated with simple image corruptions, such as blurring or adding noise, degrading image classification performance. Many methods have been…

Machine Learning · Computer Science 2023-06-16 Ian Mason , Anirban Sarkar , Tomotake Sasaki , Xavier Boix

Multi-modal entity alignment aims to identify equivalent entities between two multi-modal Knowledge graphs by integrating multi-modal data, such as images and text, to enrich the semantic representations of entities. However, existing…

Artificial Intelligence · Computer Science 2026-01-21 Zhifei Li , Ziyue Qin , Xiangyu Luo , Xiaoju Hou , Yue Zhao , Miao Zhang , Zhifang Huang , Kui Xiao , Bing Yang

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

Modality gap significantly restricts the effectiveness of multimodal fusion. Previous methods often use techniques such as diffusion models and adversarial learning to reduce the modality gap, but they typically focus on one-to-one…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Sijie Mai , Shiqin Han

Recently, vision-language models like CLIP have advanced the state of the art in a variety of multi-modal tasks including image captioning and caption evaluation. Many approaches leverage CLIP for cross-modal retrieval to condition…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Fabian Paischer , Markus Hofmarcher , Sepp Hochreiter , Thomas Adler

Vision-language models like CLIP show impressive ability to align images and text, but their training on short, concise captions makes them struggle with lengthy, detailed descriptions. Recent advances mitigate this challenge by leveraging…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Chau Truong , Hieu Ta Quang , Dung D. Le

Multi-modal image-text models such as CLIP and LiT have demonstrated impressive performance on image classification benchmarks and their zero-shot generalization ability is particularly exciting. While the top-5 zero-shot accuracies of…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Yunhao Ge , Jie Ren , Andrew Gallagher , Yuxiao Wang , Ming-Hsuan Yang , Hartwig Adam , Laurent Itti , Balaji Lakshminarayanan , Jiaping Zhao