Test-Time Adaptation for Nighttime Color-Thermal Semantic Segmentation

TL;DR

This paper introduces Night-TTA, a novel test-time adaptation framework for nighttime RGB-Thermal semantic segmentation that improves performance without access to source data, addressing domain gaps and modality discrepancies.

Contribution

The paper proposes the first TTA framework for nighttime RGBT segmentation, featuring IHR, CAR, and a collaborative learning scheme to enhance prediction accuracy during testing.

Findings

Achieves state-of-the-art performance with a 13.07% boost in mIoU.

Effectively reduces domain gap between day and night images.

Improves cross-modal consistency and segmentation accuracy.

Abstract

The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for RGB-Thermal (RGB-T) semantic segmentation. However, it is essentially hampered by two critical problems: 1) the day-night gap of RGB images is larger than that of thermal images, and 2) the class-wise performance of RGB images at night is not consistently higher or lower than that of thermal images. we propose the first test-time adaptation (TTA) framework, dubbed Night-TTA, to address the problems for nighttime RGBT semantic segmentation without access to the source (daytime) data during adaptation. Our method enjoys three key technical parts. Firstly, as one modality (e.g., RGB) suffers from a larger domain gap than that of the other (e.g., thermal), Imaging Heterogeneity Refinement (IHR) employs an interaction branch on the basis of RGB and thermal branches to prevent cross-modal discrepancy and performance degradation. Then, Class Aware Refinement (CAR) is introduced to obtain reliable ensemble logits based on pixel-level distribution aggregation of the three branches. In addition, we also design a specific learning scheme for our TTA framework, which enables the ensemble logits and three student logits to collaboratively learn to improve the quality of predictions during the testing phase of our Night TTA. Extensive experiments show that our method achieves state-of-the-art (SoTA) performance with a 13.07% boost in mIoU.