中文
相关论文

相关论文: Devil is in the Details: Density Guidance for Deta…

200 篇论文

Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency. However, such fine-tuned models are not robust; they often fail to compose with concepts of pretrained…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Kyungmin Lee , Sangkyung Kwak , Kihyuk Sohn , Jinwoo Shin

Dataset distillation has emerged as an effective strategy, significantly reducing training costs and facilitating more efficient model deployment. Recent advances have leveraged generative models to distill datasets by capturing the…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Jeffrey A. Chan-Santiago , Praveen Tirupattur , Gaurav Kumar Nayak , Gaowen Liu , Mubarak Shah

The performance of computer vision models in certain real-world applications (e.g., rare wildlife observation) is limited by the small number of available images. Expanding datasets using pre-trained generative models is an effective way to…

计算机视觉与模式识别 · 计算机科学 2024-12-25 Changjian Chen , Fei Lv , Yalong Guan , Pengcheng Wang , Shengjie Yu , Yifan Zhang , Zhuo Tang

Image-text matching has been a long-standing problem, which seeks to connect vision and language through semantic understanding. Due to the capability to manage large-scale raw data, unsupervised hashing-based approaches have gained…

计算机视觉与模式识别 · 计算机科学 2024-05-21 Fan Zhang , Xian-Sheng Hua , Chong Chen , Xiao Luo

Classifier-guided diffusion models generate conditional samples by augmenting the reverse-time score with the gradient of the log-probability predicted by a probabilistic classifier. In practice, this classifier is usually obtained by…

机器学习 · 统计学 2026-02-06 Sharan Sahu , Arisina Banerjee , Yuchen Wu

Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have much worse density modeling performance compared to…

机器学习 · 计算机科学 2019-05-17 Jonathan Ho , Xi Chen , Aravind Srinivas , Yan Duan , Pieter Abbeel

Diffusion models have recently gained prominence in offline reinforcement learning due to their ability to effectively learn high-performing, generalizable policies from static datasets. Diffusion-based planners facilitate long-horizon…

机器学习 · 计算机科学 2025-10-27 Donghyeon Ki , JunHyeok Oh , Seong-Woong Shim , Byung-Jun Lee

We present a novel visualization-driven illumination model for density plots, a new technique to enhance density plots by effectively revealing the detailed structures in high- and medium-density regions and outliers in low-density regions,…

图形学 · 计算机科学 2025-07-24 Xin Chen , Yunhai Wang , Huaiwei Bao , Kecheng Lu , Jaemin Jo , Chi-Wing Fu , Jean-Daniel Fekete

We present an novel framework for efficiently and effectively extending the powerful continuous diffusion processes to discrete modeling. Previous approaches have suffered from the discrepancy between discrete data and continuous modeling.…

机器学习 · 计算机科学 2024-10-31 Yuxuan Gu , Xiaocheng Feng , Lei Huang , Yingsheng Wu , Zekun Zhou , Weihong Zhong , Kun Zhu , Bing Qin

Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Pascal Zwick , Nils Friederich , Maximilian Beichter , Lennart Hilbert , Ralf Mikut , Oliver Bringmann

Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Jeeyung Kim , Ze Wang , Qiang Qiu

The first order derivative of a data density can be estimated efficiently by denoising score matching, and has become an important component in many applications, such as image generation and audio synthesis. Higher order derivatives…

机器学习 · 计算机科学 2021-11-09 Chenlin Meng , Yang Song , Wenzhe Li , Stefano Ermon

Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion process by gradients…

计算机视觉与模式识别 · 计算机科学 2023-03-17 Bahjat Kawar , Roy Ganz , Michael Elad

Although neural networks achieve promising performance in many tasks, they may still fail when encountering some examples and bring about risks to applications. To discover risky samples, previous literature attempts to search for patterns…

机器学习 · 计算机科学 2025-12-23 Han Yu , Hao Zou , Xingxuan Zhang , Zhengyi Wang , Yue He , Kehan Li , Peng Cui

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

计算机视觉与模式识别 · 计算机科学 2022-04-14 Robin Rombach , Andreas Blattmann , Dominik Lorenz , Patrick Esser , Björn Ommer

Large-scale text-to-image generative models have been a ground-breaking development in generative AI, with diffusion models showing their astounding ability to synthesize convincing images following an input text prompt. The goal of image…

计算机视觉与模式识别 · 计算机科学 2023-09-28 Kai Wang , Fei Yang , Shiqi Yang , Muhammad Atif Butt , Joost van de Weijer

Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional discrete data, such as language, is still limited. In this…

机器学习 · 计算机科学 2024-11-06 Itai Gat , Tal Remez , Neta Shaul , Felix Kreuk , Ricky T. Q. Chen , Gabriel Synnaeve , Yossi Adi , Yaron Lipman

Diffusion Models have demonstrated remarkable performance in image generation. However, their demanding computational requirements for training have prompted ongoing efforts to enhance the quality of generated images through modifications…

计算机视觉与模式识别 · 计算机科学 2023-11-21 Eleftherios Tsonis , Paraskevi Tzouveli , Athanasios Voulodimos

Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Ayush Shrivastava , Connelly Barnes , Xuaner Zhang , Lingzhi Zhang , Andrew Owens , Sohrab Amirghodsi , Eli Shechtman

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…

图像与视频处理 · 电气工程与系统科学 2024-09-26 Lingchen Sun , Rongyuan Wu , Jie Liang , Zhengqiang Zhang , Hongwei Yong , Lei Zhang
‹ 上一页 1 8 9 10 下一页 ›