VisDA: The Visual Domain Adaptation Challenge

TL;DR

The paper introduces the VisDA dataset and challenge, a large-scale benchmark for unsupervised domain adaptation focusing on simulation-to-reality transfer in image classification and segmentation tasks.

Contribution

It provides the largest dataset to date for cross-domain object classification and segmentation, and establishes a benchmark for evaluating domain adaptation methods.

Findings

Baseline models show significant room for improvement.

The dataset enables comprehensive evaluation of domain adaptation techniques.

Performance varies notably across different models and tasks.

Abstract

We present the 2017 Visual Domain Adaptation (VisDA) dataset and challenge, a large-scale testbed for unsupervised domain adaptation across visual domains. Unsupervised domain adaptation aims to solve the real-world problem of domain shift, where machine learning models trained on one domain must be transferred and adapted to a novel visual domain without additional supervision. The VisDA2017 challenge is focused on the simulation-to-reality shift and has two associated tasks: image classification and image segmentation. The goal in both tracks is to first train a model on simulated, synthetic data in the source domain and then adapt it to perform well on real image data in the unlabeled test domain. Our dataset is the largest one to date for cross-domain object classification, with over 280K images across 12 categories in the combined training, validation and testing domains. The image segmentation dataset is also large-scale with over 30K images across 18 categories in the three domains. We compare VisDA to existing cross-domain adaptation datasets and provide a baseline performance analysis using various domain adaptation models that are currently popular in the field.