# Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019

arXiv: https://arxiv.org/abs/1910.03548 · HTML: https://mlsanity.com/paper/1910.03548/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2019.

## Built on by (most cited first, 2 of 2)

- [Transferrable Contrastive Learning for Visual Domain Adaptation](https://mlsanity.com/paper/2112.07516/) (2021)
- [Mini but Mighty: Finetuning ViTs with Mini Adapters](https://mlsanity.com/paper/2311.03873/) (2023)

## Abstract (arXiv)

This notebook paper presents an overview and comparative analysis of our systems designed for the following two tasks in Visual Domain Adaptation Challenge (VisDA-2019): multi-source domain adaptation and semi-supervised domain adaptation. Multi-Source Domain Adaptation: We investigate both pixel-level and feature-level adaptation for multi-source domain adaptation task, i.e., directly hallucinating labeled target sample via CycleGAN and learning domain-invariant feature representations through self-learning. Moreover, the mechanism of fusing features from different backbones is further studied to facilitate the learning of domain-invariant classifiers. Source code and pre-trained models are available at urlhttps://github.com/Panda-Peter/visda2019-multisource. Semi-Supervised Domain Adaptation: For this task, we adopt a standard self-learning framework to construct a classifier based on the labeled source and target data, and generate the pseudo labels for unlabeled target data. These target data with pseudo labels are then exploited to re-training the classifier in a following iteration. Furthermore, a prototype-based classification module is additionally utilized to strengthen the predictions. Source code and pre-trained models are available at urlhttps://github.com/Panda-Peter/visda2019-semisupervised.