Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation

by   Qijun Luo, et al.

Semi-supervised domain adaptation (SSDA), which aims to learn models in a partially labeled target domain with the assistance of the fully labeled source domain, attracts increasing attention in recent years. To explicitly leverage the labeled data in both domains, we naturally introduce a conditional GAN framework to transfer images without changing the semantics in SSDA. However, we identify a label-domination problem in such an approach. In fact, the generator tends to overlook the input source image and only memorizes prototypes of each class, which results in unsatisfactory adaptation performance. To this end, we propose a simple yet effective Relaxed conditional GAN (Relaxed cGAN) framework. Specifically, we feed the image without its label to our generator. In this way, the generator has to infer the semantic information of input data. We formally prove that its equilibrium is desirable and empirically validate its practical convergence and effectiveness in image transfer. Additionally, we propose several techniques to make use of unlabeled data in the target domain, enhancing the model in SSDA settings. We validate our method on the well-adopted datasets: Digits, DomainNet, and Office-Home. We achieve state-of-the-art performance on DomainNet, Office-Home and most digit benchmarks in low-resource and high-resource settings.


page 3

page 13

page 14

page 15


MiCo: Mixup Co-Training for Semi-Supervised Domain Adaptation

Semi-supervised domain adaptation (SSDA) aims to adapt models from a lab...

Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation

Semi-supervised domain adaptation (SSDA) methods have demonstrated great...

Pred Guide: Labeled Target Class Prediction for Guiding Semi-Supervised Domain Adaptation

Semi-supervised domain adaptation aims to classify data belonging to a t...

Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer

Semi-supervised domain adaptation (SSDA) aims to solve tasks in target d...

Cluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification

Semi-supervised domain adaptation is a technique to build a classifier f...

Dual-Teacher++: Exploiting Intra-domain and Inter-domain Knowledge with Reliable Transfer for Cardiac Segmentation

Annotation scarcity is a long-standing problem in medical image analysis...

Semi-supervised Optimal Transport with Self-paced Ensemble for Cross-hospital Sepsis Early Detection

The utilization of computer technology to solve problems in medical scen...

Please sign up or login with your details

Forgot password? Click here to reset