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

TL;DR

This paper provides an overview and analysis of systems for multi-source and semi-supervised domain adaptation in visual tasks, exploring pixel and feature-level techniques, feature fusion, and pseudo-labeling strategies.

Contribution

It introduces a comprehensive comparison of adaptation methods for VisDA-2019, including novel feature fusion and prototype-based classification approaches.

Findings

Pixel-level and feature-level adaptation improve target domain performance.

Feature fusion from multiple backbones enhances domain-invariant learning.

Self-learning with pseudo labels and prototype modules boosts semi-supervised adaptation.

Abstract

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 \url{https://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 \url{https://github.com/Panda-Peter/visda2019-semisupervised}.