Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones. This catastrophic forgetting phenomenon impacts on the deployment of artificial intelligence in real world scenarios where systems need to learn new and different representations over time. Current approaches for incremental learning deal only with image classification and object detection tasks, while in this work we formally introduce incremental learning for semantic segmentation. We tackle the problem applying various knowledge distillation techniques on the previous model. In this way, we retain the information about learned classes, whilst updating the current model to learn the new ones. We developed four main methodologies of knowledge distillation working on both output layers and internal feature representations. We do not store any image belonging to previous training stages and only the last model is used to preserve high accuracy on previously learned classes. Extensive experimental results on the Pascal VOC2012 and MSRC-v2 datasets show the effectiveness of the proposed approaches in several incremental learning scenarios.
翻译:深层学习架构在现场理解问题中显示了显著成果,然而,在需要学习渐进式新任务而又不忘旧任务时,它们表现出了关键的成绩下降。这一灾难性的遗忘现象影响到在现实世界情景中部署人工智能,而系统需要了解新的和不同的代表形式。当前渐进式学习方法仅涉及图像分类和对象探测任务,而在此工作中我们正式引入对语义分割的渐进式学习。我们在前一个模型中应用各种知识蒸馏技术来解决这个问题。这样,我们在更新当前模式以学习新课程的同时,保留了有关学习班的信息。我们开发了四种主要的知识蒸馏方法,在产出层和内部特征展示方面都工作。我们没有储存属于以往培训阶段的任何图像,只有最后一种模型用于保持以往学习班级的高精度。Pscal VOC2012和MSRC-V2数据集的广泛实验结果显示了在若干渐进式学习情景中拟议方法的有效性。