Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods, making it especially relevant in the context of intelligent vehicles. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. The source code is publicly available at https://github.com/yihong-97/Source-free-IAPC.

翻译：域自适应语义分割能够实现对真实驾驶场景中逐像素的鲁棒理解。作为更实用的技术，无源域适应解决了典型无监督域适应方法中的数据隐私和存储限制问题，使其在智能车辆领域尤为重要。该方法利用预训练的源模型和无标签的目标数据，实现目标域的适应。然而，在缺乏源数据和目标标签的情况下，现有方案无法充分减少域迁移的影响，也无法完全利用目标数据的信息。本文提出了一种基于重要性感知与原型对比（IAPC）学习的端到端无源域适应语义分割方法。所提出的IAPC框架能够从预训练的源模型中有效提取域不变知识，并从无标签的目标域中学习域特定知识。具体而言，针对源模型在目标域预测中存在的域迁移问题，我们提出了一种面向偏置目标预测概率分布的重要性感知机制，以从源模型中提取域不变知识。进一步地，我们引入了一种原型对比策略，包括原型对称交叉熵损失和原型增强交叉熵损失，以不依赖标签的方式学习目标域内知识。在两个域自适应语义分割基准上的全面实验表明，所提出的端到端IAPC方法优于现有最先进方法。源代码已公开发布于 https://github.com/yihong-97/Source-free-IAPC。