Adaptation Across Extreme Variations using Unlabeled Domain Bridges
arXiv:1906.02238
Abstract
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.
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Deep Domain Confusion: Maximizing for Domain Invariance
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Semantic Foggy Scene Understanding with Synthetic Data
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- Domain Separation Networks
- Joint Distribution Optimal Transportation for Domain Adaptation
- Multiple Source Domain Adaptation with Adversarial Training of Neural Networks