Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation

by   Subhankar Roy, et al.

In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains. We identify two key aspects that can help to alleviate multiple domain-shifts in the MTDA: feature aggregation and curriculum learning. To this end, we propose Curriculum Graph Co-Teaching (CGCT) that uses a dual classifier head, with one of them being a graph convolutional network (GCN) which aggregates features from similar samples across the domains. To prevent the classifiers from over-fitting on its own noisy pseudo-labels we develop a co-teaching strategy with the dual classifier head that is assisted by curriculum learning to obtain more reliable pseudo-labels. Furthermore, when the domain labels are available, we propose Domain-aware Curriculum Learning (DCL), a sequential adaptation strategy that first adapts on the easier target domains, followed by the harder ones. We experimentally demonstrate the effectiveness of our proposed frameworks on several benchmarks and advance the state-of-the-art in the MTDA by large margins (e.g. +5.6


Cross-domain error minimization for unsupervised domain adaptation

Unsupervised domain adaptation aims to transfer knowledge from a labeled...

Curriculum Manager for Source Selection in Multi-Source Domain Adaptation

The performance of Multi-Source Unsupervised Domain Adaptation depends s...

Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning

By leveraging data from a fully labeled source domain, unsupervised doma...

Unsupervised Compound Domain Adaptation for Face Anti-Spoofing

We address the problem of face anti-spoofing which aims to make the face...

Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation

In this work we address multi-target domain adaptation (MTDA) in semanti...

Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation

To learn target discriminative representations, using pseudo-labels is a...

Unsupervised Domain Adaptation through Iterative Consensus Shift in a Multi-Task Graph

Babies learn with very little supervision by observing the surrounding w...

Please sign up or login with your details

Forgot password? Click here to reset