DeepAI AI Chat
Log In Sign Up

Adaptation Across Extreme Variations using Unlabeled Domain Bridges

by   Shuyang Dai, et al.

We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and intra-domain variation. While deep domain adaptation methods have been realized by reducing the domain discrepancy, these are difficult to apply when domains are significantly unalike. In this work, we propose to decompose domain discrepancy into multiple but smaller, and thus easier to minimize, discrepancies by introducing unlabeled bridging domains that connect the source and target domains. We realize our proposal through an extension of the domain adversarial neural network with multiple discriminators, each of which accounts for reducing discrepancies between unlabeled (bridge, target) domains and a mix of all precedent domains including source. We validate the effectiveness of our method on several adaptation tasks including object recognition and semantic segmentation.


page 1

page 6

page 8

page 15

page 16

page 17


Learning Domain Adaptive Features with Unlabeled Domain Bridges

Conventional cross-domain image-to-image translation or unsupervised dom...

CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) aims to align the labeled source di...

Unsupervised Scene Adaptation with Memory Regularization in vivo

We consider the unsupervised scene adaptation problem of learning from b...

Domain Adaptive Neural Networks for Object Recognition

We propose a simple neural network model to deal with the domain adaptat...

Self-Adversarial Disentangling for Specific Domain Adaptation

Domain adaptation aims to bridge the domain shifts between the source an...

Compound Domain Adaptation in an Open World

Existing works on domain adaptation often assume clear boundaries betwee...

Gradual Domain Adaptation without Indexed Intermediate Domains

The effectiveness of unsupervised domain adaptation degrades when there ...