中文
相关论文

相关论文: Latent Directions: A Simple Pathway to Bias Mitiga…

200 篇论文

Text-to-image generation intends to automatically produce a photo-realistic image, conditioned on a textual description. It can be potentially employed in the field of art creation, data augmentation, photo-editing, etc. Although many…

计算机视觉与模式识别 · 计算机科学 2022-03-01 Zhenxing Zhang , Lambert Schomaker

Large-scale text-to-image generative models have been a revolutionary breakthrough in the evolution of generative AI, allowing us to synthesize diverse images that convey highly complex visual concepts. However, a pivotal challenge in…

计算机视觉与模式识别 · 计算机科学 2022-11-24 Narek Tumanyan , Michal Geyer , Shai Bagon , Tali Dekel

Generative models make huge progress to the photorealistic image synthesis in recent years. To enable human to steer the image generation process and customize the output, many works explore the interpretable dimensions of the latent space…

计算机视觉与模式识别 · 计算机科学 2024-01-11 Jianyuan Wang , Lalit Bhagat , Ceyuan Yang , Yinghao Xu , Yujun Shen , Hongdong Li , Bolei Zhou

Denoising Diffusion models are gaining increasing popularity in the field of generative modeling for several reasons, including the simple and stable training, the excellent generative quality, and the solid probabilistic foundation. In…

计算机视觉与模式识别 · 计算机科学 2023-01-19 Andrea Asperti , Davide Evangelista , Samuele Marro , Fabio Merizzi

A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images. But existing techniques for identifying these…

计算机视觉与模式识别 · 计算机科学 2021-10-11 Sarah Schwettmann , Evan Hernandez , David Bau , Samuel Klein , Jacob Andreas , Antonio Torralba

Generative models have been very popular in the recent years for their image generation capabilities. GAN-based models are highly regarded for their disentangled latent space, which is a key feature contributing to their success in…

计算机视觉与模式识别 · 计算机科学 2023-12-12 Yusuf Dalva , Pinar Yanardag

Generating multiple distinct subjects remains a challenge for existing text-to-image diffusion models. Complex prompts often lead to subject leakage, causing inaccuracies in quantities, attributes, and visual features. Preventing leakage…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Omer Dahary , Yehonathan Cohen , Or Patashnik , Kfir Aberman , Daniel Cohen-Or

The heightened realism of AI-generated images can be attributed to the rapid development of synthetic models, including generative adversarial networks (GANs) and diffusion models (DMs). The malevolent use of synthetic images, such as the…

计算机视觉与模式识别 · 计算机科学 2025-05-01 Haiwei Wu , Jiantao Zhou , Shile Zhang

Dataset bias is a significant challenge in machine learning, where specific attributes, such as texture or color of the images are unintentionally learned resulting in detrimental performance. To address this, previous efforts have focused…

计算机视觉与模式识别 · 计算机科学 2024-06-11 Donggeun Ko , Sangwoo Jo , Dongjun Lee , Namjun Park , Jaekwang Kim

We develop an approach for text-to-image generation that embraces additional retrieval images, driven by a combination of implicit visual guidance loss and generative objectives. Unlike most existing text-to-image generation methods which…

计算机视觉与模式识别 · 计算机科学 2022-08-19 Xin Yuan , Zhe Lin , Jason Kuen , Jianming Zhang , John Collomosse

The rapid development of generative artificial intelligence (AI) has introduced significant opportunities for enhancing the efficiency and accuracy of image transmission within semantic communication systems. Despite these advancements,…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Qiyu Ma , Wanli Ni , Zhijin Qin

Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image…

计算机视觉与模式识别 · 计算机科学 2020-06-16 Wei Xiong , Yutong He , Yixuan Zhang , Wenhan Luo , Lin Ma , Jiebo Luo

Diffusion-based Image Editing has achieved significant success in recent years. However, it remains challenging to achieve high-quality image editing while maintaining the background similarity without sacrificing speed or memory…

图形学 · 计算机科学 2025-09-03 Siyi Liu , Weiming Chen , Yushun Tang , Zhihai He

Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…

计算机视觉与模式识别 · 计算机科学 2021-10-05 Zhiheng Li , Chenliang Xu

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

计算机视觉与模式识别 · 计算机科学 2021-03-30 Shuhan Tan , Yujun Shen , Bolei Zhou

Text-to-Image (T2I) generation is enabling new applications that support creators, designers, and general end users of productivity software by generating illustrative content with high photorealism starting from a given descriptive text as…

计算机与社会 · 计算机科学 2023-04-14 Ranjita Naik , Besmira Nushi

Measuring biases of vision systems with respect to protected attributes like gender and age is critical as these systems gain widespread use in society. However, significant correlations between attributes in benchmark datasets make it…

计算机视觉与模式识别 · 计算机科学 2021-03-26 Chandan Singh , Guha Balakrishnan , Pietro Perona

The proliferation of text-to-image diffusion models (T2I DMs) has led to an increased presence of AI-generated images in daily life. However, biased T2I models can generate content with specific tendencies, potentially influencing people's…

计算机视觉与模式识别 · 计算机科学 2025-04-03 Huayang Huang , Xiangye Jin , Jiaxu Miao , Yu Wu

In text-to-image personalization, a timely and crucial challenge is the tendency of generated images overfitting to the biases present in the reference images. We initiate our study with a comprehensive categorization of the biases into…

计算机视觉与模式识别 · 计算机科学 2024-03-25 Jimyeong Kim , Jungwon Park , Wonjong Rhee

Generative adversarial networks (GANs) can now generate photo-realistic images. However, how to best control the image content remains an open challenge. We introduce LatentKeypointGAN, a two-stage GAN internally conditioned on a set of…

计算机视觉与模式识别 · 计算机科学 2023-06-10 Xingzhe He , Bastian Wandt , Helge Rhodin