English
Related papers

Related papers: Improving Cross-modal Alignment with Synthetic Pai…

200 papers

Contrastive models like CLIP have been shown to learn robust representations of images that capture both semantics and style. To leverage these representations for image generation, we propose a two-stage model: a prior that generates a…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Aditya Ramesh , Prafulla Dhariwal , Alex Nichol , Casey Chu , Mark Chen

Contrastive vision-language models, such as CLIP, have garnered considerable attention for various downstream tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Yichao Cai , Yuhang Liu , Zhen Zhang , Javen Qinfeng Shi

In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text)…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Haicheng Wang , Chen Ju , Weixiong Lin , Shuai Xiao , Mengting Chen , Yixuan Huang , Chang Liu , Mingshuai Yao , Jinsong Lan , Ying Chen , Qingwen Liu , Yanfeng Wang

Recent years have witnessed the fast development of large-scale pre-training frameworks that can extract multi-modal representations in a unified form and achieve promising performances when transferred to downstream tasks. Nevertheless,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Xuran Pan , Tianzhu Ye , Dongchen Han , Shiji Song , Gao Huang

Data-driven approaches hold promise for audio captioning. However, the development of audio captioning methods can be biased due to the limited availability and quality of text-audio data. This paper proposes a SynthAC framework, which…

Sound · Computer Science 2023-09-19 Feiyang Xiao , Qiaoxi Zhu , Jian Guan , Xubo Liu , Haohe Liu , Kejia Zhang , Wenwu Wang

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is paid to the interpretation of CLIP. We propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Chenyang Zhao , Kun Wang , Janet H. Hsiao , Antoni B. Chan

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

Computer Vision and Pattern Recognition · Computer Science 2025-09-05 Yingxuan Li , Jiafeng Mao , Yusuke Matsui

Most text-to-image customization techniques fine-tune models on a small set of \emph{personal concept} images captured in minimal contexts. This often results in the model becoming overfitted to these training images and unable to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Taewook Kim , Wei Chen , Qiang Qiu

Image-text matching (ITM) is a fundamental problem in computer vision. The key issue lies in jointly learning the visual and textual representation to estimate their similarity accurately. Most existing methods focus on feature enhancement…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Xuri Ge , Fuhai Chen , Songpei Xu , Fuxiang Tao , Jie Wang , Joemon M. Jose

Unsupervised image captioning is a challenging task that aims at generating captions without the supervision of image-sentence pairs, but only with images and sentences drawn from different sources and object labels detected from the…

Computation and Language · Computer Science 2021-06-02 Ukyo Honda , Yoshitaka Ushiku , Atsushi Hashimoto , Taro Watanabe , Yuji Matsumoto

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Weiquan Huang , Aoqi Wu , Yifan Yang , Xufang Luo , Yuqing Yang , Usman Naseem , Chunyu Wang , Chunyu Wang , Qi Dai , Xiyang Dai , Dongdong Chen , Chong Luo , Lili Qiu , Liang Hu

Text-to-image diffusion-based generative models have the stunning ability to generate photo-realistic images and achieve state-of-the-art low FID scores on challenging image generation benchmarks. However, one of the primary failure modes…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Arman Zarei , Keivan Rezaei , Samyadeep Basu , Mehrdad Saberi , Mazda Moayeri , Priyatham Kattakinda , Soheil Feizi

In recent years, the field of vision-language model pre-training has experienced rapid advancements, driven primarily by the continuous enhancement of textual capabilities in large language models. However, existing training paradigms for…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Xinsong Zhang , Yarong Zeng , Xinting Huang , Hu Hu , Runquan Xie , Han Hu , Zhanhui Kang

Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Qiying Yu , Quan Sun , Xiaosong Zhang , Yufeng Cui , Fan Zhang , Yue Cao , Xinlong Wang , Jingjing Liu

Modern image captioning models are usually trained with text similarity objectives. However, since reference captions in public datasets often describe the most salient common objects, models trained with text similarity objectives tend to…

Computation and Language · Computer Science 2023-03-31 Jaemin Cho , Seunghyun Yoon , Ajinkya Kale , Franck Dernoncourt , Trung Bui , Mohit Bansal

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…

Computer Vision and Pattern Recognition · Computer Science 2025-02-20 Hong-You Chen , Zhengfeng Lai , Haotian Zhang , Xinze Wang , Marcin Eichner , Keen You , Meng Cao , Bowen Zhang , Yinfei Yang , Zhe Gan

Contrastive Language-Image Pretraining (CLIP) has demonstrated great zero-shot performance for matching images and text. However, it is still challenging to adapt vision-lanaguage pretrained models like CLIP to compositional image and text…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Kenan Jiang , Xuehai He , Ruize Xu , Xin Eric Wang

The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions. A primary challenge in this task is bridging the substantial representational gap between visual and…

Computation and Language · Computer Science 2025-01-20 Delong Liu , Haiwen Li , Zhicheng Zhao , Yuan Dong

Customization of text-to-image models enables users to insert new concepts or objects and generate them in unseen settings. Existing methods either rely on comparatively expensive test-time optimization or train encoders on single-image…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Nupur Kumari , Xi Yin , Jun-Yan Zhu , Ishan Misra , Samaneh Azadi

A significant ``modality gap" exists between the abundance of text-only data and the increasing power of multimodal models. This work systematically investigates whether images generated on-the-fly by Text-to-Image (T2I) models can serve as…

Multimedia · Computer Science 2026-03-04 Yuesheng Huang , Peng Zhang , Xiaoxin Wu , Riliang Liu , Jiaqi Liang
‹ Prev 1 3 4 5 6 7 10 Next ›