Domain adaptive semantic segmentation is recognized as a promising technique to alleviate the domain shift between the labeled source domain and the unlabeled target domain in many real-world applications, such as automatic pilot. However, large amounts of source domain data often introduce significant costs in storage and training, and sometimes the source data is inaccessible due to privacy policies. To address these problems, we investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain, and then adapting to the target domain without accessing source data anymore. Since there is no supervision from the source domain data, many self-training methods tend to fall into the ``winner-takes-all'' dilemma, where the {\it majority} classes totally dominate the segmentation networks and the networks fail to classify the {\it minority} classes. Consequently, we propose an effective framework for this challenging problem with two components: positive learning and negative learning. In positive learning, we select the class-balanced pseudo-labeled pixels with intra-class threshold, while in negative learning, for each pixel, we investigate which category the pixel does not belong to with the proposed heuristic complementary label selection. Notably, our framework can be easily implemented and incorporated with other methods to further enhance the performance. Extensive experiments on two widely-used synthetic-to-real benchmarks demonstrate our claims and the effectiveness of our framework, which outperforms the baseline with a large margin. Code is available at \url{https://github.com/fumyou13/LDBE}.
翻译:为解决这些问题,我们调查了无源的适应性语义分割法,认为该模型是在源域上预先培训的,然后适应目标域,不再访问源域数据。由于源域数据不受源域数据的监管,许多自培训方法往往会进入“双向取全”的两难境地,在此情况下,源域数据往往在储存和培训方面产生巨大的成本,有时由于隐私政策而无法获得源数据。为了解决这些问题,我们调查了无源数据的地区适应性语义分割法,假设该模型是在源域上预先培训的,然后适应目标域,而不再访问源域数据。由于源域域数据没有受到监管,因此许多自培训方法往往会进入“双向取全方位”的两难境地,在“双向”类别中,“多数”类完全主宰了分类网络的储存和培训,而网络未能对源域数据进行分类。因此,我们为这一具有挑战性的问题提出了一个有效的框架:积极的学习和消极的学习。在积极学习中,我们选择了等级平衡的假标的像项,而无需再访问源域数据。在每等域数据域数据域数据中学习,同时,我们调查哪个类的“双级的“双向”框架,我们可轻易地展示了“基数”的“基数”的“基值框架,我们“基数”和“基数”中的“基数”的“基数”的“基数”与“基数”与“基数”与“基数”与“基数”与“基数”与“基数”比”。