Generate To Adapt: Aligning Domains using Generative Adversarial Networks
This addresses the problem of domain shift for computer vision applications, offering a novel GAN-based method that works across diverse datasets, though it is incremental in leveraging existing adversarial frameworks.
The paper tackles domain adaptation in computer vision by aligning source and target distributions in a learned joint feature space using a generative adversarial network, achieving state-of-the-art performance on tasks like digit classification and object recognition across multiple datasets.
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.