中文
相关论文

相关论文: Unsupervised Image-to-Image Translation with Self-…

200 篇论文

Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain transfer often operate on data on which the modes of the…

机器学习 · 计算机科学 2019-05-31 Mikołaj Bińkowski , R Devon Hjelm , Aaron Courville

Unpaired Image-to-image Translation is a new rising and challenging vision problem that aims to learn a mapping between unaligned image pairs in diverse domains. Recent advances in this field like MUNIT and DRIT mainly focus on…

计算机视觉与模式识别 · 计算机科学 2019-05-07 Zhiqiang Shen , Mingyang Huang , Jianping Shi , Xiangyang Xue , Thomas Huang

Unpaired Image-to-Image Translation (UIT) focuses on translating images among different domains by using unpaired data, which has received increasing research focus due to its practical usage. However, existing UIT schemes defect in the…

计算机视觉与模式识别 · 计算机科学 2019-04-30 Xinyang Li , Jie Hu , Shengchuan Zhang , Xiaopeng Hong , Qixiang Ye , Chenglin Wu , Rongrong Ji

Over the past few years, image-to-image (I2I) translation methods have been proposed to translate a given image into diverse outputs. Despite the impressive results, they mainly focus on the I2I translation between two domains, so the…

计算机视觉与模式识别 · 计算机科学 2022-02-08 Somi Jeong , Jiyoung Lee , Kwanghoon Sohn

Image-to-image translation models have shown remarkable ability on transferring images among different domains. Most of existing work follows the setting that the source domain and target domain keep the same at training and inference…

计算机视觉与模式识别 · 计算机科学 2021-07-21 Jianxin Lin , Yingce Xia , Sen Liu , Shuqin Zhao , Zhibo Chen

We propose a unified Generative Adversarial Network (GAN) for controllable image-to-image translation, i.e., transferring an image from a source to a target domain guided by controllable structures. In addition to conditioning on a…

计算机视觉与模式识别 · 计算机科学 2020-10-28 Hao Tang , Hong Liu , Nicu Sebe

We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type…

计算机视觉与模式识别 · 计算机科学 2020-10-16 L. Xiao , J. Xu , D. Zhao , Z. Wang , L. Wang , Y. Nie , B. Dai

Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the datasets of some specific scenes or applications. If we train…

计算机视觉与模式识别 · 计算机科学 2022-03-09 Tianxiao Zhang , Wenchi Ma , Guanghui Wang

Recent Image-to-Image Translation algorithms have achieved significant progress in neural style transfer and image attribute manipulation tasks. However, existing approaches require exhaustively labelling training data, which is labor…

计算机视觉与模式识别 · 计算机科学 2020-06-01 Jichao Zhang , Yezhi Shu , Songhua Xu , Gongze Cao , Fan Zhong , Meng Liu , Xueying Qin

Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes…

计算机视觉与模式识别 · 计算机科学 2019-04-18 Hao Tang , Dan Xu , Nicu Sebe , Yanzhi Wang , Jason J. Corso , Yan Yan

Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend…

计算机视觉与模式识别 · 计算机科学 2021-10-01 George Eskandar , Mohamed Abdelsamad , Karim Armanious , Bin Yang

Domain adaptation is of huge interest as labeling is an expensive and error-prone task, especially when labels are needed on pixel-level like in semantic segmentation. Therefore, one would like to be able to train neural networks on…

计算机视觉与模式识别 · 计算机科学 2022-08-19 Annika Mütze , Matthias Rottmann , Hanno Gottschalk

An unsupervised image-to-image translation (UI2I) task deals with learning a mapping between two domains without paired images. While existing UI2I methods usually require numerous unpaired images from different domains for training, there…

计算机视觉与模式识别 · 计算机科学 2020-08-11 Jianxin Lin , Yingxue Pang , Yingce Xia , Zhibo Chen , Jiebo Luo

Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their…

计算机视觉与模式识别 · 计算机科学 2020-08-25 Jinyu Yang , Weizhi An , Sheng Wang , Xinliang Zhu , Chaochao Yan , Junzhou Huang

Recent advances in deep learning, in particular enabled by hardware advances and big data, have provided impressive results across a wide range of computational problems such as computer vision, natural language, or reinforcement learning.…

计算机视觉与模式识别 · 计算机科学 2021-12-23 Ileana Rugina , Rumen Dangovski , Mark Veillette , Pooya Khorrami , Brian Cheung , Olga Simek , Marin Soljačić

Despite significant advances in image-to-image (I2I) translation with generative adversarial networks (GANs), it remains challenging to effectively translate an image to a set of diverse images in multiple target domains using a single pair…

计算机视觉与模式识别 · 计算机科学 2022-06-30 Shihua Huang , Cheng He , Ran Cheng

Generative adversarial networks (GANs) have ushered in a revolution in image-to-image translation. The development and proliferation of GANs raises an interesting question: can we train a GAN to remove an object, if present, from an image…

图像与视频处理 · 电气工程与系统科学 2019-08-30 Md Mahfuzur Rahman Siddiquee , Zongwei Zhou , Nima Tajbakhsh , Ruibin Feng , Michael B. Gotway , Yoshua Bengio , Jianming Liang

Unsupervised image-to-image translation (UNIT) aims at learning a mapping between several visual domains by using unpaired training images. Recent studies have shown remarkable success for multiple domains but they suffer from two main…

计算机视觉与模式识别 · 计算机科学 2020-03-24 Yahui Liu , Marco De Nadai , Jian Yao , Nicu Sebe , Bruno Lepri , Xavier Alameda-Pineda

Using real road testing to optimize autonomous driving algorithms is time-consuming and capital-intensive. To solve this problem, we propose a GAN-based model that is capable of generating high-quality images across different domains. We…

计算机视觉与模式识别 · 计算机科学 2023-02-24 Hanzhen Zhang , Liguo Zhou , Ruining Wang , Alois Knoll

For unsupervised image-to-image translation, we propose a discriminator architecture which focuses on the statistical features instead of individual patches. The network is stabilized by distribution matching of key statistical features at…

计算机视觉与模式识别 · 计算机科学 2021-08-30 Xuning Shao , Weidong Zhang