论文标题
班级和域内的语义细分的持续学习
Continual Learning for Class- and Domain-Incremental Semantic Segmentation
论文作者
论文摘要
持续深度学习的领域是一个新兴领域，已经取得了很多进步。但是，同时仅根据图像分类的任务进行测试，这在智能车辆领域无关。直到最近，才提出了类型语义分割的方法。但是，所有这些方法都是基于某种形式的知识蒸馏。目前，尚未对基于重播的方法进行调查，这些方法通常在连续的环境中用于对象识别。同时，尽管无监督的语义分割的域适应性获得了很多吸引力，但在持续环境中有关域内收入学习的调查并未得到充分研究。因此，我们工作的目的是评估和调整已建立的解决方案，以持续对象识别语义分割任务，并为持续的语义分割任务提供基线方法和评估协议。我们首先介绍了类和域内的分割的评估协议，并分析选定的方法。我们表明，语义分割变化的任务的性质与图像分类相比最有效地减轻忘记。特别是，在课堂学习中，学习知识蒸馏被证明是至关重要的工具，而在领域内的学习重播方法中是最有效的方法。
The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of intelligent vehicles. Only recently approaches for class-incremental semantic segmentation were proposed. However, all of those approaches are based on some form of knowledge distillation. At the moment there are no investigations on replay-based approaches that are commonly used for object recognition in a continual setting. At the same time while unsupervised domain adaption for semantic segmentation gained a lot of traction, investigations regarding domain-incremental learning in an continual setting is not well-studied. Therefore, the goal of our work is to evaluate and adapt established solutions for continual object recognition to the task of semantic segmentation and to provide baseline methods and evaluation protocols for the task of continual semantic segmentation. We firstly introduce evaluation protocols for the class- and domain-incremental segmentation and analyze selected approaches. We show that the nature of the task of semantic segmentation changes which methods are most effective in mitigating forgetting compared to image classification. Especially, in class-incremental learning knowledge distillation proves to be a vital tool, whereas in domain-incremental learning replay methods are the most effective method.
