Opposite Structure Learning for Semi-supervised Domain Adaptation

by   Can Qin, et al.

Current adversarial adaptation methods attempt to align the cross-domain features whereas two challenges remain unsolved: 1) conditional distribution mismatch between different domains and 2) the bias of decision boundary towards the source domain. To solve these challenges, we propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures (UODA). UODA consists of a generator and two classifiers (i.e., the source-based and the target-based classifiers respectively) which are trained with opposite forms of losses for a unified object. The target-based classifier attempts to cluster the target features to improve intra-class density and enlarge inter-class divergence. Meanwhile, the source-based classifier is designed to scatter the source features to enhance the smoothness of decision boundary. Through the alternation of source-feature expansion and target-feature clustering procedures, the target features are well-enclosed within the dilated boundary of the corresponding source features. This strategy effectively makes the cross-domain features precisely aligned. To overcome the model collapse through training, we progressively update the measurement of distance and the feature representation on both domains via an adversarial training paradigm. Extensive experiments on the benchmarks of DomainNet and Office-home datasets demonstrate the effectiveness of our approach over the state-of-the-art method.


Semi-supervised Domain Adaptive Structure Learning

Semi-supervised domain adaptation (SSDA) is quite a challenging problem ...

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

In semi-supervised domain adaptation (SSDA), a few labeled target sample...

Cross-Domain Few-Shot Classification via Inter-Source Stylization

Cross-Domain Few Shot Classification (CDFSC) leverages prior knowledge l...

Explaining Cross-Domain Recognition with Interpretable Deep Classifier

The recent advances in deep learning predominantly construct models in t...

Dynamic Feature Alignment for Semi-supervised Domain Adaptation

Most research on domain adaptation has focused on the purely unsupervise...

Transferable Semantic Augmentation for Domain Adaptation

Domain adaptation has been widely explored by transferring the knowledge...

Adversarial Bipartite Graph Learning for Video Domain Adaptation

Domain adaptation techniques, which focus on adapting models between dis...

Code Repositories


This is the official implementation of SDM-21 paper - "Contradictory Structure Learning for Semi-supervised Domain Adaptation".

view repo

Please sign up or login with your details

Forgot password? Click here to reset