PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding

TL;DR

PCoTTA introduces a novel continual test-time adaptation framework for multi-task point cloud understanding, employing prototype mixing, feature shifting, and contrastive learning to improve transferability across changing domains.

Contribution

It proposes a new multi-task continual adaptation framework with three innovative components, addressing catastrophic forgetting and domain shift in point cloud understanding.

Findings

Outperforms existing methods in transferability benchmarks

Effectively mitigates catastrophic forgetting during adaptation

Enhances model robustness in dynamic target domains

Abstract

In this paper, we present PCoTTA, an innovative, pioneering framework for Continual Test-Time Adaptation (CoTTA) in multi-task point cloud understanding, enhancing the model's transferability towards the continually changing target domain. We introduce a multi-task setting for PCoTTA, which is practical and realistic, handling multiple tasks within one unified model during the continual adaptation. Our PCoTTA involves three key components: automatic prototype mixture (APM), Gaussian Splatted feature shifting (GSFS), and contrastive prototype repulsion (CPR). Firstly, APM is designed to automatically mix the source prototypes with the learnable prototypes with a similarity balancing factor, avoiding catastrophic forgetting. Then, GSFS dynamically shifts the testing sample toward the source domain, mitigating error accumulation in an online manner. In addition, CPR is proposed to pull the nearest learnable prototype close to the testing feature and push it away from other prototypes, making each prototype distinguishable during the adaptation. Experimental comparisons lead to a new benchmark, demonstrating PCoTTA's superiority in boosting the model's transferability towards the continually changing target domain.