Generate To Adapt: Aligning Domains using Generative Adversarial Networks

2017/04/06 by Swami Sankaranarayanan, Yogesh Balaji, Sankaranarayanan, Swami +5 · 6 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.1704.01705

openalex publication_date 2017/04/06 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28

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.

Cited by

• Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
• VirDA: Reusing Backbone for Unsupervised Domain Adaptation with Visual Reprogramming
• Global Variational Inference Enhanced Robust Domain Adaptation
• Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios
• Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments
• Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation

Related

• Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
• A Review on Domain Adaption and Generative Adversarial Networks(GANs)
• Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks
• Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks
• Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption