MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge

Abstract

We present a domain adaptation (DA) system that can be used in multi-source and semi-supervised settings. Using the proposed method we achieved 2nd place on multi-source track and 3rd place on semi-supervised track of the VisDA 2019 challenge (http://ai.bu.edu/visda-2019/). The source code of the method is available at https://github.com/filaPro/visda2019.

arXiv commentaccepted at TASK-CV 2019 at ICCV

References in corpus (4)

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• mixup: Beyond Empirical Risk Minimization
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Moment Matching for Multi-Source Domain Adaptation

Cited by in corpus (4)

• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
• Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
• Semi-supervised Domain Adaptation for Semantic Segmentation