Continual Learning for Class- and Domain-Incremental Semantic Segmentation
| Autor: | Jürgen Beyerer, Tobias Kalb, Masoud Roschani, Miriam Ruf |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Class (computer programming) Contextual image classification Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Deep learning Cognitive neuroscience of visual object recognition Computer Science - Computer Vision and Pattern Recognition Image segmentation Machine learning computer.software_genre Semantics Task (project management) Segmentation Artificial intelligence business computer |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|