English
Related papers

Related papers: Does language help generalization in vision models…

200 papers

Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same representation space, which implicitly assumes a one-to-one…

Computation and Language · Computer Science 2020-02-10 Patrick Bordes , Eloi Zablocki , Laure Soulier , Benjamin Piwowarski , Patrick Gallinari

Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The…

Computer Vision and Pattern Recognition · Computer Science 2026-01-26 Nahid Alam , Leema Krishna Murali , Siddhant Bharadwaj , Patrick Liu , Timothy Chung , Drishti Sharma , Akshata A , Kranthi Kiran , Wesley Tam , Bala Krishna S Vegesna

Compositional generalization, the ability of intelligent models to extrapolate understanding of components to novel compositions, is a fundamental yet challenging facet in AI research, especially within multimodal environments. In this…

Computation and Language · Computer Science 2023-11-09 Danial Kamali , Parisa Kordjamshidi

In multi-label classification, machine learning encounters the challenge of domain generalization when handling tasks with distributions differing from the training data. Existing approaches primarily focus on vision object recognition and…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Yuxin Qiao , Keqin Li , Junhong Lin , Rong Wei , Chufeng Jiang , Yang Luo , Haoyu Yang

We examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architecture is introduced that outperform its equivalent trained on language alone with a 2\% decrease in…

Computation and Language · Computer Science 2019-06-05 Alexander G. Ororbia , Ankur Mali , Matthew A. Kelly , David Reitter

Audio-visual zero-shot learning methods commonly build on features extracted from pre-trained models, e.g. video or audio classification models. However, existing benchmarks predate the popularization of large multi-modal models, such as…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 David Kurzendörfer , Otniel-Bogdan Mercea , A. Sophia Koepke , Zeynep Akata

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic…

Machine Learning · Computer Science 2020-02-19 Chen Xing , Negar Rostamzadeh , Boris N. Oreshkin , Pedro O. Pinheiro

The ratio of outlier parameters in language pre-training models and vision pre-training models differs significantly, making cross-modality (language and vision) inherently more challenging than cross-domain adaptation. As a result, many…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Yaxin Luo , Zhiqiang Shen

It is expensive to collect training data for every possible domain that a vision model may encounter when deployed. We instead consider how simply verbalizing the training domain (e.g. "photos of birds") as well as domains we want to extend…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Lisa Dunlap , Clara Mohri , Devin Guillory , Han Zhang , Trevor Darrell , Joseph E. Gonzalez , Aditi Raghunathan , Anja Rohrbach

Recently there has been a significant surge in multimodal learning in terms of both image-to-text and text-to-image generation. However, the success is typically limited to English, leaving other languages largely behind. Building a…

Computation and Language · Computer Science 2024-03-25 Jinyi Hu , Yuan Yao , Chongyi Wang , Shan Wang , Yinxu Pan , Qianyu Chen , Tianyu Yu , Hanghao Wu , Yue Zhao , Haoye Zhang , Xu Han , Yankai Lin , Jiao Xue , Dahai Li , Zhiyuan Liu , Maosong Sun

Multimodal learning leverages the integration of diverse data modalities to enhance performance in complex tasks. Yet, it frequently encounters incomplete or redundant modality data in real-world scenarios. This paper presents a…

Machine Learning · Computer Science 2026-05-05 Richeng Zhou , Xuelin Zhang , Liyuan Liu

Large language models (LLMs) have been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach for zero-shot image classification using multimodal LLMs.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Abdelrahman Abdelhamed , Mahmoud Afifi , Alec Go

When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Chih-Yao Ma , Yannis Kalantidis , Ghassan AlRegib , Peter Vajda , Marcus Rohrbach , Zsolt Kira

Recently, we have witnessed the great success of the generalist model in natural language processing. The generalist model is a general framework trained with massive data and is able to process various downstream tasks simultaneously.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Ziyi Wang , Yongming Rao , Shuofeng Sun , Xinrun Liu , Yi Wei , Xumin Yu , Zuyan Liu , Yanbo Wang , Hongmin Liu , Jie Zhou , Jiwen Lu

Despite significant progress in multimodal language models (LMs), it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models. To address this question, we propose a novel…

Computation and Language · Computer Science 2025-10-21 Zhihui Yang , Yupei Wang , Kaijie Mo , Zhe Zhao , Renfen Hu

We analyze the grounded SCAN (gSCAN) benchmark, which was recently proposed to study systematic generalization for grounded language understanding. First, we study which aspects of the original benchmark can be solved by commonly used…

Computation and Language · Computer Science 2021-09-28 Linlu Qiu , Hexiang Hu , Bowen Zhang , Peter Shaw , Fei Sha

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on the instance-level…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Shengbang Tong , Zhuang Liu , Yuexiang Zhai , Yi Ma , Yann LeCun , Saining Xie

This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-16 Po-Yao Huang , Mandela Patrick , Junjie Hu , Graham Neubig , Florian Metze , Alexander Hauptmann

We introduce a language-grounded visual prompting method to adapt the visual encoder of vision-language models for downstream tasks. By capitalizing on language integration, we devise a parameter-efficient strategy to adjust the input of…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Nilakshan Kunananthaseelan , Jing Zhang , Mehrtash Harandi

Large-scale language models have shown the ability to adapt to a new task via conditioning on a few demonstrations (i.e., in-context learning). However, in the vision-language domain, most large-scale pre-trained vision-language (VL) models…

Computation and Language · Computer Science 2023-06-05 Masoud Monajatipoor , Liunian Harold Li , Mozhdeh Rouhsedaghat , Lin F. Yang , Kai-Wei Chang