@jk_itwm

Generate To Adapt: Aligning Domains using Generative Adversarial Networks

, , , and . (2017)cite arxiv:1704.01705Comment: Accepted as spotlight talk at CVPR 2018. Code available here: https://github.com/yogeshbalaji/Generate_To_Adapt.

Abstract

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.

Description

Generate To Adapt: Aligning Domains using Generative Adversarial Networks

Links and resources

URL:
BibTeX key:
sankaranarayanan2017generate
search on:

Comments and Reviews  
(0)

There is no review or comment yet. You can write one!

Tags


Cite this publication