中文
相关论文

相关论文: DECOR:Decomposition and Projection of Text Embeddi…

200 篇论文

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Huiqiang Chen , Tianqing Zhu , Linlin Wang , Xin Yu , Longxiang Gao , Wanlei Zhou

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…

计算机视觉与模式识别 · 计算机科学 2025-01-28 Yucong Luo , Mingyue Cheng , Jie Ouyang , Xiaoyu Tao , Qi Liu

Text-to-image (T2I) models based on diffusion and transformer architectures advance rapidly. They are often pretrained on large corpora, and openly shared on a model platform, such as HuggingFace. Users can then build up AI applications,…

机器学习 · 计算机科学 2025-08-18 Basile Lewandowski , Robert Birke , Lydia Y. Chen

Text-to-Image (T2I) diffusion models (DM) have garnered widespread adoption due to their capability in generating high-fidelity outputs and accessibility to anyone able to put imagination into words. However, DMs are often predisposed to…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Zhe Jin , Tat-Seng Chua

Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Sarah Rastegar , Violeta Chatalbasheva , Sieger Falkena , Anuj Singh , Yanbo Wang , Tejas Gokhale , Hamid Palangi , Hadi Jamali-Rad

Recent advancements in text-to-image (T2I) generative models have shown remarkable capabilities in producing diverse and imaginative visuals based on text prompts. Despite the advancement, these diffusion models sometimes struggle to…

计算机视觉与模式识别 · 计算机科学 2023-11-30 Xiaohui Chen , Yongfei Liu , Yingxiang Yang , Jianbo Yuan , Quanzeng You , Li-Ping Liu , Hongxia Yang

Diffusion-driven text-to-image (T2I) generation has achieved remarkable advancements in recent years. To further improve T2I models' capability in numerical and spatial reasoning, layout is employed as an intermedium to bridge large…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Yuhao Jia , Wenhan Tan

Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused to produce inappropriate content. Existing safety measures,…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Hongxiang Zhang , Yifeng He , Hao Chen

Text-to-image (T2I) diffusion models have made remarkable strides in generating and editing high-fidelity images from text. Yet, these models remain fundamentally generic, failing to adapt to the nuanced aesthetic preferences of individual…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Connor Dunlop , Matthew Zheng , Kavana Venkatesh , Pinar Yanardag

Text embeddings are essential for many tasks, such as document retrieval, clustering, and semantic similarity assessment. In this paper, we study how to contrastively train text embedding models in a compute-optimal fashion, given a suite…

机器学习 · 计算机科学 2024-11-22 Alicja Ziarko , Albert Q. Jiang , Bartosz Piotrowski , Wenda Li , Mateja Jamnik , Piotr Miłoś

In the text-to-image generation field, recent remarkable progress in Stable Diffusion makes it possible to generate rich kinds of novel photorealistic images. However, current models still face misalignment issues (e.g., problematic spatial…

计算机视觉与模式识别 · 计算机科学 2023-08-15 Leigang Qu , Shengqiong Wu , Hao Fei , Liqiang Nie , Tat-Seng Chua

We propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models that changes the inference procedure, does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based…

Text-to-Image (T2I) generation has made significant advancements with the advent of diffusion models. These models exhibit remarkable abilities to produce images based on textual prompts. Current T2I models allow users to specify object…

计算机视觉与模式识别 · 计算机科学 2024-07-11 Muhammad Atif Butt , Kai Wang , Javier Vazquez-Corral , Joost van de Weijer

Text-to-Image (T2I) models excel at synthesizing concepts such as nouns, appearances, and styles. To enable customized content creation based on a few example images of a concept, methods such as Textual Inversion and DreamBooth invert the…

计算机视觉与模式识别 · 计算机科学 2024-09-30 Saman Motamed , Danda Pani Paudel , Luc Van Gool

Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g. color, the exact visual nuances along…

计算机视觉与模式识别 · 计算机科学 2024-04-04 Sharon Lee , Yunzhi Zhang , Shangzhe Wu , Jiajun Wu

Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggle…

计算机视觉与模式识别 · 计算机科学 2023-03-07 Rinon Gal , Moab Arar , Yuval Atzmon , Amit H. Bermano , Gal Chechik , Daniel Cohen-Or

Recent advances in large-scale text-to-image (T2I) diffusion models have enabled a variety of downstream applications, including style customization, subject-driven personalization, and conditional generation. As T2I models require…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Zilan Wang , Junfeng Guo , Jiacheng Zhu , Yiming Li , Heng Huang , Muhao Chen , Zhengzhong Tu

Both text-to-image generation and large language models (LLMs) have made significant advancements. However, many text-to-image models still employ the somewhat outdated T5 and CLIP as their text encoders. In this work, we investigate the…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Andrew Z. Wang , Songwei Ge , Tero Karras , Ming-Yu Liu , Yogesh Balaji

Text-to-image (T2I) generation has made remarkable progress, yet existing systems still lack intuitive control over spatial composition, object consistency, and multi-step editing. We present $\textbf{LayerCraft}$, a modular framework that…

机器学习 · 计算机科学 2025-10-20 Yuyao Zhang , Jinghao Li , Yu-Wing Tai

We consider the problem of customizing text-to-image diffusion models with user-supplied reference images. Given new prompts, the existing methods can capture the key concept from the reference images but fail to align the generated image…

计算机视觉与模式识别 · 计算机科学 2024-07-01 Aishwarya Agarwal , Srikrishna Karanam , Balaji Vasan Srinivasan