Image to Image Translation for Domain Adaptation

Abstract

We propose a general framework for unsupervised domain adaptation, which allows deep neural networks trained on a source domain to be tested on a different target domain without requiring any training annotations in the target domain. This is achieved by adding extra networks and losses that help regularize the features extracted by the backbone encoder network. To this end we propose the novel use of the recently proposed unpaired image-toimage translation framework to constrain the features extracted by the encoder network. Specifically, we require that the features extracted are able to reconstruct the images in both domains. In addition we require that the distribution of features extracted from images in the two domains are indistinguishable. Many recent works can be seen as specific cases of our general framework. We apply our method for domain adaptation between MNIST, USPS, and SVHN datasets, and Amazon, Webcam and DSLR Office datasets in classification tasks, and also between GTA5 and Cityscapes datasets for a segmentation task. We demonstrate state of the art performance on each of these datasets.

References in corpus (14)

• Deep Residual Learning for Image Recognition
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Densely Connected Convolutional Networks
• Improved Training of Wasserstein GANs
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Adversarial Discriminative Domain Adaptation
• Virtual Worlds as Proxy for Multi-Object Tracking Analysis
• Dilated Residual Networks
• Least Squares Generative Adversarial Networks
• Playing for Data: Ground Truth from Computer Games
• The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

Cited by in corpus (13)

• UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models
• Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
• Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation
• Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
• Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
• Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
• Learning a Domain-Invariant Embedding for Unsupervised Domain Adaptation Using Class-Conditioned Distribution Alignment
• Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning
• Beyond Domain Adaptation: Unseen Domain Encapsulation via Universal Non-volume Preserving Models
• Unsupervised Domain Adaptation using Generative Models and Self-ensembling
• DLOW: Domain Flow for Adaptation and Generalization
• Attribute-Driven Spontaneous Motion in Unpaired Image Translation
• Memory-guided Unsupervised Image-to-image Translation