APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds

TL;DR

APCoTTA introduces a novel continual test-time adaptation framework for airborne LiDAR point cloud segmentation, addressing domain shifts, catastrophic forgetting, and error accumulation with new techniques and benchmarks.

Contribution

It proposes a tailored CTTA framework with gradient-driven layer selection, entropy-based consistency loss, and parameter interpolation, along with new benchmarks for ALS point cloud segmentation.

Findings

APCoTTA improves mIoU by approximately 9% and 14% over direct inference on two benchmarks.

The framework effectively mitigates catastrophic forgetting and error accumulation during adaptation.

New benchmarks ISPRSC and H3DC facilitate future research in ALS point cloud CTTA.

Abstract

Airborne laser scanning (ALS) point cloud semantic segmentation is a fundamental task for large-scale 3D scene understanding. Fixed models deployed in real-world scenarios often suffer from performance degradation due to continuous domain shifts caused by environmental and sensor changes. Continuous Test-Time Adaptation (CTTA) enables adaptation to evolving unlabeled domains, but its application to ALS point clouds remains underexplored, hindered by the lack of benchmarks and the risks of catastrophic forgetting and error accumulation. To address these challenges, we propose APCoTTA (ALS Point cloud Continuous Test-Time Adaptation), a novel CTTA framework tailored for ALS point cloud semantic segmentation. APCoTTA consists of three key components. First, we adapt a gradient-driven layer selection mechanism for ALS point clouds, selectively updating low-confidence layers while freezing stable ones to preserve source knowledge and mitigate catastrophic forgetting. Second, an entropy-based consistency loss discards unreliable samples and enforces consistency regularization solely on reliable ones, effectively reducing error accumulation and improving adaptation stability. Third, a random parameter interpolation mechanism stochastically blends adapted parameters with source model parameters, further balancing target adaptation and source knowledge retention. Finally, we construct two benchmarks, ISPRSC and H3DC, to address the lack of CTTA benchmarks for ALS point cloud segmentation. Extensive experiments demonstrate that APCoTTA achieves superior performance on both benchmarks, improving mIoU by approximately 9\% and 14\% over direct inference. The new benchmarks and code are available at https://github.com/Gaoyuan2/APCoTTA.