Enhancing Visual Domain Adaptation with Source Preparation
Preprint
Abstract
Robotic Perception in diverse domains such as low-light scenarios, where new modalities like thermal imaging and specialized night-vision sensors are increasingly employed, remains a challenge. Largely, this is due to the limited availability of labeled data. Existing Domain Adaptation (DA) techniques, while promising to leverage labels from existing well-lit RGB images, fail to consider the characteristics of the source domain itself. We holistically account for this factor by proposing Source Preparation (SP), a method to mitigate source domain biases. Our Almost Unsupervised Domain Adaptation (AUDA) framework, a label-efficient semi-supervised approach for robotic scenarios -- employs Source Preparation (SP), Unsupervised Domain Adaptation (UDA) and Supervised Alignment (SA) from limited labeled data. We introduce CityIntensified, a novel dataset comprising temporally aligned image pairs captured from a high-sensitivity camera and an intensifier camera for semantic segmentation and object detection in low-light settings. We demonstrate the effectiveness of our method in semantic segmentation, with experiments showing that SP enhances UDA across a range of visual domains, with improvements up to 40.64% in mIoU over baseline, while making target models more robust to real-world shifts within the target domain. We show that AUDA is a label-efficient framework for effective DA, significantly improving target domain performance with only tens of labeled samples from the target domain.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Domain-Specific Bias Filtering for Single Labeled Domain GeneralizationInternational Journal of Computer Vision, 2022
- Classes Matter: A Fine-Grained Adversarial Approach to Cross-Domain Semantic Segmentation2020
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning2020
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation2019
- Bidirectional Learning for Domain Adaptation of Semantic Segmentation2019
- Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training2018
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation2018
- Learning to Adapt Structured Output Space for Semantic Segmentation2018
- Image Style Transfer Using Convolutional Neural Networks2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016