English
Related papers

Related papers: TIMA: Text-Image Mutual Awareness for Balancing Ze…

200 papers

Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Md Zarif Hossain , Ahmed Imteaj

The fine-tuning of large vision-language foundation models remains an underexplored area, particularly regarding its impact on learning gains and catastrophic forgetting. Inspired by the significance of modality gaps in contrastive…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Laura Niss , Kevin Vogt-Lowell , Theodoros Tsiligkaridis

Image stitching seamlessly integrates images captured from varying perspectives into a single wide field-of-view image. Such integration not only broadens the captured scene but also augments holistic perception in computer vision…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Zhiying Jiang , Xingyuan Li , Jinyuan Liu , Xin Fan , Risheng Liu

The core problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes. Previous approaches train the feature pyramid and detection head from scratch, which…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Relja Arandjelović , Alex Andonian , Arthur Mensch , Olivier J. Hénaff , Jean-Baptiste Alayrac , Andrew Zisserman

Automatic image matting (AIM) refers to estimating the soft foreground from an arbitrary natural image without any auxiliary input like trimap, which is useful for image editing. Prior methods try to learn semantic features to aid the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-16 Jizhizi Li , Jing Zhang , Dacheng Tao

Generalized zero-shot learning recognizes inputs from both seen and unseen classes. Yet, existing methods tend to be biased towards the classes seen during training. In this paper, we strive to mitigate this bias. We propose a bias-aware…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 William Thong , Cees G. M. Snoek

Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Aditya Ramesh , Mikhail Pavlov , Gabriel Goh , Scott Gray , Chelsea Voss , Alec Radford , Mark Chen , Ilya Sutskever

Most existing zero-shot learning methods consider the problem as a visual semantic embedding one. Given the demonstrated capability of Generative Adversarial Networks(GANs) to generate images, we instead leverage GANs to imagine unseen…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Yizhe Zhu , Mohamed Elhoseiny , Bingchen Liu , Xi Peng , Ahmed Elgammal

Text-to-Image Person Retrieval (TIPR) is a cross-modal matching task designed to identify the person images that best correspond to a given textual description. The key difficulty in TIPR is to realize robust correspondence between the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Hao Yin , Xin Man , Feiyu Chen , Jie Shao , Heng Tao Shen

Recently, remote sensing image captioning has gained significant attention in the remote sensing community. Due to the significant differences in spatial resolution of remote sensing images, existing methods in this field have predominantly…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Cong Yang , Zuchao Li , Lefei Zhang

Prompt tuning has been employed as an efficient way to adapt large vision-language pre-trained models (e.g. CLIP) to various downstream tasks in data-limited or label-limited settings. Nonetheless, visual data (e.g., images) is by default…

Computer Vision and Pattern Recognition · Computer Science 2022-12-21 Zixian Guo , Bowen Dong , Zhilong Ji , Jinfeng Bai , Yiwen Guo , Wangmeng Zuo

The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…

Machine Learning · Computer Science 2021-11-30 Hui Ye , Xiulong Yang , Martin Takac , Rajshekhar Sunderraman , Shihao Ji

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

Recent advances in text-based image editing have enabled fine-grained manipulation of visual content guided by natural language. However, such methods are susceptible to adversarial attacks. In this work, we propose a novel attack that…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Matteo Trippodo , Federico Becattini , Lorenzo Seidenari

State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt perturbations applied at inference time, such as random…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Yunzhuo Chen , Jordan Vice , Naveed Akhtar , Nur Al Hasan Haldar , Ajmal Mian

We consider the problem of single-source domain generalization. Existing methods typically rely on extensive augmentations to synthetically cover diverse domains during training. However, they struggle with semantic shifts (e.g., background…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Aishwarya Agarwal , Srikrishna Karanam , Vineet Gandhi

Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Yucong Luo , Mingyue Cheng , Jie Ouyang , Xiaoyu Tao , Qi Liu

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

Image rescaling aims to learn the optimal low-resolution (LR) image that can be accurately reconstructed to its original high-resolution (HR) counterpart, providing an efficient image processing and storage method for ultra-high definition…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Ce Wang , Zhenyu Hu , Wanjie Sun , Zhenzhong Chen

Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised adaptation (UA) for fine-grained classification with VLMs…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Eman Ali , Sathira Silva , Chetan Arora , Muhammad Haris Khan