Unsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data and is, in most cases, carried out in offline manner. However, domain changes may occur continuously and unpredictably during deployment (e.g. sudden weather changes). In such conditions, deep neural networks witness dramatic drops in accuracy and offline adaptation may not be enough to contrast it. In this paper, we tackle Online Domain Adaptation (OnDA) for semantic segmentation. We design a pipeline that is robust to continuous domain shifts, either gradual or sudden, and we evaluate it in the case of rainy and foggy scenarios. Our experiments show that our framework can effectively adapt to new domains during deployment, while not being affected by catastrophic forgetting of the previous domains.
翻译:无人监督的域适应(UDA)旨在缩小培训和测试数据之间的域间差距,在多数情况下都是以离线方式进行的,然而,在部署期间,域变化可能持续发生,而且难以预测(例如突发的天气变化),在这种情况下,深神经网络的精确度和离线适应率的急剧下降可能不足以与之形成对比。在本文中,我们处理在线域适应(ONDA)的语义分割问题。我们设计了一条管道,该管道能够逐渐或突然地持续域变换,我们在雨季和雾雾情况下对其进行评估。我们的实验表明,在部署期间,我们的框架可以有效地适应新的域,同时不会受到过去域被灾难性地遗忘的影响。