Open Set Domain Adaptation by Backpropagation

Abstract

Numerous algorithms have been proposed for transferring knowledge from a label-rich domain (source) to a label-scarce domain (target). Almost all of them are proposed for a closed-set scenario, where the source and the target domain completely share the class of their samples. We call the shared class the \doublequote{known class.} However, in practice, when samples in target domain are not labeled, we cannot know whether the domains share the class. A target domain can contain samples of classes that are not shared by the source domain. We call such classes the \doublequote{unknown class} and algorithms that work well in the open set situation are very practical. However, most existing distribution matching methods for domain adaptation do not work well in this setting because unknown target samples should not be aligned with the source. In this paper, we propose a method for an open set domain adaptation scenario which utilizes adversarial training. A classifier is trained to make a boundary between the source and the target samples whereas a generator is trained to make target samples far from the boundary. Thus, we assign two options to the feature generator: aligning them with source known samples or rejecting them as unknown target samples. This approach allows extracting features that separate unknown target samples from known target samples. Our method was extensively evaluated in domain adaptation setting and outperformed other methods with a large margin in most settings.

arXiv commentAccepted by ECCV2018

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unsupervised Domain Adaptation with Residual Transfer Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Separation Networks
• Unsupervised Image-to-Image Translation Networks
• Adversarial Discriminative Domain Adaptation
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Unsupervised Cross-Domain Image Generation
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation

Cited by in corpus (7)

• Recent Advances in Open Set Recognition: A Survey
• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
• Minimum Class Confusion for Versatile Domain Adaptation
• OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
• Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• MMF: A loss extension for feature learning in open set recognition