中文
相关论文

相关论文: Cross Domain Image Generation through Latent Space…

200 篇论文

Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has become a highly effective way for conditional image synthesis,…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Zheyuan Zhan , Defang Chen , Jian-Ping Mei , Zhenghe Zhao , Jiawei Chen , Chun Chen , Siwei Lyu , Can Wang

An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as…

计算与语言 · 计算机科学 2017-09-25 Wei-Ning Hsu , Yu Zhang , James Glass

Neural networks used for image classification tasks in critical applications must be tested with sufficient realistic data to assure their correctness. To effectively test an image classification neural network, one must obtain realistic…

机器学习 · 计算机科学 2020-02-18 Taejoon Byun , Abhishek Vijayakumar , Sanjai Rayadurgam , Darren Cofer

Current deep domain adaptation methods used in computer vision have mainly focused on learning discriminative and domain-invariant features across different domains. In this paper, we present a novel approach that bridges the domain gap by…

计算机视觉与模式识别 · 计算机科学 2019-03-26 Jinyong Hou , Xuejie Ding , Jeremiah D. Deng , Stephen Cranefield

Generative adversarial networks (GANs) are a powerful framework for generative tasks. However, they are difficult to train and tend to miss modes of the true data generation process. Although GANs can learn a rich representation of the…

机器学习 · 计算机科学 2017-11-27 Robin Winter , Djork-Arné Clevert

The generative autoencoders, such as the variational autoencoders or the adversarial autoencoders, have achieved great success in lots of real-world applications, including image generation, and signal communication. However, little concern…

机器学习 · 计算机科学 2023-07-06 Mingfei Lu , Badong Chen

In this paper, we investigate the problem of multi-domain translation: given an element $a$ of domain $A$, we would like to generate a corresponding $b$ sample in another domain $B$, and vice versa. Acquiring supervision in multiple domains…

机器学习 · 计算机科学 2022-12-08 Tsiry Mayet , Simon Bernard , Clement Chatelain , Romain Herault

Image generation abilities of text-to-image diffusion models have significantly advanced, yielding highly photo-realistic images from descriptive text and increasing the viability of leveraging synthetic images to train computer vision…

计算机视觉与模式识别 · 计算机科学 2025-02-10 Jiahui Chen , Amy Zhang , Adriana Romero-Soriano

Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware…

计算机视觉与模式识别 · 计算机科学 2019-04-04 Rui Liu , Yu Liu , Xinyu Gong , Xiaogang Wang , Hongsheng Li

Generative Adversarial Networks (GANs) have received a great deal of attention due in part to recent success in generating original, high-quality samples from visual domains. However, most current methods only allow for users to guide this…

图形学 · 计算机科学 2019-04-05 Eric Heim

One of the most challenges in medical imaging is the lack of data. It is proven that classical data augmentation methods are useful but still limited due to the huge variation in images. Using generative adversarial networks (GAN) is a…

图像与视频处理 · 电气工程与系统科学 2021-04-16 Amine Amyar , Su Ruan , Pierre Vera , Pierre Decazes , Romain Modzelewski

Conditional generative adversarial networks (cGANs) target at synthesizing diverse images given the input conditions and latent codes, but unfortunately, they usually suffer from the issue of mode collapse. To solve this issue, previous…

计算机视觉与模式识别 · 计算机科学 2021-04-27 Rui Liu , Yixiao Ge , Ching Lam Choi , Xiaogang Wang , Hongsheng Li

How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our…

计算机视觉与模式识别 · 计算机科学 2021-03-17 Đorđe Miladinović , Aleksandar Stanić , Stefan Bauer , Jürgen Schmidhuber , Joachim M. Buhmann

In multimodal unsupervised image-to-image translation tasks, the goal is to translate an image from the source domain to many images in the target domain. We present a simple method that produces higher quality images than current…

计算机视觉与模式识别 · 计算机科学 2019-04-09 Yazeed Alharbi , Neil Smith , Peter Wonka

The availability of data is limited in some fields, especially for object detection tasks, where it is necessary to have correctly labeled bounding boxes around each object. A notable example of such data scarcity is found in the domain of…

计算机视觉与模式识别 · 计算机科学 2024-09-11 Matteo Paiano , Stefano Martina , Carlotta Giannelli , Filippo Caruso

Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are…

The objective of domain generalization (DG) is to enable models to be robust against domain shift. DG is crucial for deploying vision-language models (VLMs) in real-world applications, yet most existing methods rely on domain labels that…

机器学习 · 计算机科学 2026-02-02 Zhixing Li , Arsham Gholamzadeh Khoee , Yinan Yu

Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explicitly utilize the underlying clustering structure in the…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Anirban Samaddar , Yixuan Sun , Viktor Nilsson , Sandeep Madireddy

Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. The conventional methods forcefully reducing the domain discrepancy in the latent space will result in the…

计算机视觉与模式识别 · 计算机科学 2020-02-13 Guanglei Yang , Haifeng Xia , Mingli Ding , Zhengming Ding

The image-to-image generation task aims to produce controllable images by leveraging conditional inputs and prompt instructions. However, existing methods often train separate control branches for each type of condition, leading to…

计算机视觉与模式识别 · 计算机科学 2025-12-16 Guoqing Zhang , Xingtong Ge , Lu Shi , Xin Zhang , Muqing Xue , Wanru Xu , Yigang Cen , Yidong Li
‹ 上一页 1 8 9 10 下一页 ›