CVAIROJun 16, 2023

Enhancing Visual Domain Adaptation with Source Preparation

arXiv:2306.10142v11 citationsh-index: 58
Originality Incremental advance
AI Analysis

This addresses domain adaptation challenges for robotics in low-light environments, though it appears incremental as it builds on existing UDA and semi-supervised methods.

The paper tackles the problem of visual domain adaptation for robotic perception in low-light scenarios by proposing Source Preparation (SP) to mitigate source domain biases, achieving improvements up to 40.64% in mIoU over baseline for semantic segmentation.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes