中文
相关论文

相关论文: SpectralCLIP: Preventing Artifacts in Text-Guided …

200 篇论文

Contrastive language-image pre-training (CLIP) models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval, where the model is required to effectively process natural language input to…

计算机视觉与模式识别 · 计算机科学 2024-02-26 Hyunjae Kim , Seunghyun Yoon , Trung Bui , Handong Zhao , Quan Tran , Franck Dernoncourt , Jaewoo Kang

We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, due to the scarcity…

计算机视觉与模式识别 · 计算机科学 2024-05-14 Wang Lin , Jingyuan Chen , Jiaxin Shi , Yichen Zhu , Chen Liang , Junzhong Miao , Tao Jin , Zhou Zhao , Fei Wu , Shuicheng Yan , Hanwang Zhang

Multi-label classification is crucial for comprehensive image understanding, yet acquiring accurate annotations is challenging and costly. To address this, a recent study suggests exploiting unsupervised multi-label classification…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Dongseob Kim , Hyunjung Shim

Despite remarkable advancements in supervised pansharpening neural networks, these methods face domain adaptation challenges of resolution due to the intrinsic disparity between simulated reduced-resolution training data and real-world…

图像与视频处理 · 电气工程与系统科学 2025-11-17 Lihua Jian , Jiabo Liu , Shaowu Wu , Lihui Chen

Continual learning aims to enable a model to incrementally learn knowledge from sequentially arrived data. Previous works adopt the conventional classification architecture, which consists of a feature extractor and a classifier. The…

计算机视觉与模式识别 · 计算机科学 2024-03-21 Runqi Wang , Xiaoyue Duan , Guoliang Kang , Jianzhuang Liu , Shaohui Lin , Songcen Xu , Jinhu Lv , Baochang Zhang

Considerable progress has recently been made in leveraging CLIP (Contrastive Language-Image Pre-Training) models for text-guided image manipulation. However, all existing works rely on additional generative models to ensure the quality of…

计算机视觉与模式识别 · 计算机科学 2023-05-09 Yiren Song , Xuning Shao , Kang Chen , Weidong Zhang , Minzhe Li , Zhongliang Jing

In this paper, we tackle an emerging computer vision task, open-vocabulary universal image segmentation, that aims to perform semantic/instance/panoptic segmentation (background semantic labeling + foreground instance segmentation) for…

计算机视觉与模式识别 · 计算机科学 2023-06-09 Zheng Ding , Jieke Wang , Zhuowen Tu

Visually grounded speech systems learn from paired images and their spoken captions. Recently, there have been attempts to utilize the visually grounded models trained from images and their corresponding text captions, such as CLIP, to…

音频与语音处理 · 电气工程与系统科学 2023-09-12 Saurabhchand Bhati , Jesús Villalba , Laureano Moro-Velazquez , Thomas Thebaud , Najim Dehak

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…

计算机视觉与模式识别 · 计算机科学 2025-02-24 Zhiyu Zhu , Zhibo Jin , Jiayu Zhang , Nan Yang , Jiahao Huang , Jianlong Zhou , Fang Chen

Contrastive Language-Image Pre-training (CLIP) plays an essential role in extracting valuable content information from images across diverse tasks. It aligns textual and visual modalities to comprehend the entire image, including all the…

计算机视觉与模式识别 · 计算机科学 2023-12-15 Zeyi Sun , Ye Fang , Tong Wu , Pan Zhang , Yuhang Zang , Shu Kong , Yuanjun Xiong , Dahua Lin , Jiaqi Wang

Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance…

计算机视觉与模式识别 · 计算机科学 2022-02-16 Junnan Li , Dongxu Li , Caiming Xiong , Steven Hoi

Generative artificial intelligence has revolutionized the exploration of chemical space, yet a critical bottleneck remains that a substantial fraction of generated molecules is synthetically inaccessible. Current solutions, such as post-hoc…

人工智能 · 计算机科学 2025-12-24 Junren Li , Luhua Lai

Recent text-to-image diffusion models are able to generate convincing results of unprecedented quality. However, it is nearly impossible to control the shapes of different regions/objects or their layout in a fine-grained fashion. Previous…

计算机视觉与模式识别 · 计算机科学 2023-09-06 Omri Avrahami , Thomas Hayes , Oran Gafni , Sonal Gupta , Yaniv Taigman , Devi Parikh , Dani Lischinski , Ohad Fried , Xi Yin

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive.…

计算机视觉与模式识别 · 计算机科学 2023-05-10 Liangliang Cao , Bowen Zhang , Chen Chen , Yinfei Yang , Xianzhi Du , Wencong Zhang , Zhiyun Lu , Yantao Zheng

The development of CLIP [Radford et al., 2021] has sparked a debate on whether language supervision can result in vision models with more transferable representations than traditional image-only methods. Our work studies this question…

计算机视觉与模式识别 · 计算机科学 2022-07-18 Shibani Santurkar , Yann Dubois , Rohan Taori , Percy Liang , Tatsunori Hashimoto

We introduce a simple method that employs pre-trained CLIP encoders to enhance model generalization in the ALFRED task. In contrast to previous literature where CLIP replaces the visual encoder, we suggest using CLIP as an additional module…

计算机视觉与模式识别 · 计算机科学 2024-06-27 Ye Won Byun , Cathy Jiao , Shahriar Noroozizadeh , Jimin Sun , Rosa Vitiello

Contrastive vision-language models, such as CLIP, have demonstrated excellent zero-shot capability across semantic recognition tasks, mainly attributed to the training on a large-scale I&1T (one Image with one Text) dataset. This kind of…

计算机视觉与模式识别 · 计算机科学 2025-03-05 Zhichao Yang , Leida Li , Pengfei Chen , Jinjian Wu , Giuseppe Valenzise

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…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Marc-Antoine Lavoie , Anas Mahmoud , Aldo Zaimi , Arsene Fansi Tchango , Steven L. Waslander

Facial stylization aims to transform facial images into appealing, high-quality stylized portraits, with the critical challenge of accurately learning the target style while maintaining content consistency with the original image. Although…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Zhanyi Lu , Yue Zhou

Diffusion models have emerged as the dominant paradigm for style transfer, but their text-driven mechanism is hindered by a core limitation: it treats textual descriptions as uniform, monolithic guidance. This limitation overlooks the…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Yuanlin Yang , Quanjian Song , Zhexian Gao , Ge Wang , Shanshan Li , Xiaoyan Zhang