DeepAI AI Chat
Log In Sign Up

Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning

by   Xinyang Huang, et al.

In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. Many existing methods ignore the benefits of making full use of the labeled target samples from multi-level. To make better use of this additional data, we propose a novel Prototype-based Multi-level Learning (ProML) framework to better tap the potential of labeled target samples. To achieve intra-domain adaptation, we first introduce a pseudo-label aggregation based on the intra-domain optimal transport to help the model align the feature distribution of unlabeled target samples and the prototype. At the inter-domain level, we propose a cross-domain alignment loss to help the model use the target prototype for cross-domain knowledge transfer. We further propose a dual consistency based on prototype similarity and linear classifier to promote discriminative learning of compact target feature representation at the batch level. Extensive experiments on three datasets, including DomainNet, VisDA2017, and Office-Home demonstrate that our proposed method achieves state-of-the-art performance in SSDA.


page 3

page 7


Multi-level Consistency Learning for Semi-supervised Domain Adaptation

Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned...

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

In semi-supervised domain adaptation, a few labeled samples per class in...

RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Network

Cross-domain few-shot segmentation (CD-FSS) aims to achieve semantic seg...

Opposite Structure Learning for Semi-supervised Domain Adaptation

Current adversarial adaptation methods attempt to align the cross-domain...

Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning

Domain adaptation enhances generalizability of a model across domains wi...

Locality Preserving Joint Transfer for Domain Adaptation

Domain adaptation aims to leverage knowledge from a well-labeled source ...

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...