arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1704.01705cs.CV
收藏

生成以适应:使用生成对抗网络对齐域

Generate To Adapt: Aligning Domains using Generative Adversarial Networks

University of Maryland(马里兰大学);UMIACS(马里兰大学高级计算机研究所)

Swami Sankaranarayanan, Yogesh Balaji, Carlos D. Castillo, Rama Chellappa

摘要:

领域自适应是计算机视觉中的一个研究热点。在这项工作中,我们提出了一种方法,利用无监督的数据,使源和目标分布更接近学习的联合特征空间。我们通过在学习的嵌入和生成对抗网络之间引入共生关系来实现这一点。这与使用对抗框架来生成真实数据并使用这些数据重新训练深度模型的方法形成对比。我们通过对三个不同难度的任务进行实验来证明我们方法的强度和通用性:(1)数字分类(MNIST,SVHN和USPS数据集)(2)使用OFFICE数据集的对象识别和(3)从合成数据到真实数据的领域自适应。我们的方法在大多数实验环境中都达到了最先进的性能,并且是迄今为止唯一一种基于GAN的方法,该方法已被证明在不同的数据集(如OFFICE和DIGITS)上都能很好地工作。

英文摘要:

Domain Adaptation is an actively researched problem in Computer Vision. In this work, we propose an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space. We accomplish this by inducing a symbiotic relationship between the learned embedding and a generative adversarial network. This is in contrast to methods which use the adversarial framework for realistic data generation and retraining deep models with such data. We demonstrate the strength and generality of our approach by performing experiments on three different tasks with varying levels of difficulty: (1) Digit classification (MNIST, SVHN and USPS datasets) (2) Object recognition using OFFICE dataset and (3) Domain adaptation from synthetic to real data. Our method achieves state-of-the art performance in most experimental settings and by far the only GAN-based method that has been shown to work well across different datasets such as OFFICE and DIGITS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑