To accommodate rapid changes in the real world, cognition system of humans is capable continually learning concepts. On contrary, conventional deep models lack this capability preserving previously learned knowledge. When a neural network fine-tuned to learn new tasks, its performance on trained tasks will significantly deteriorate. Many recent works incremental object detection tackle problem ...

An assurance case for a critical system is valid that at particular point in time, such as when the delivered to certification authority review. The argument structured around evidence exists time. However, modern cases are rarely one-off exercises. More information might become available (e.g., field data) could strengthen (or weaken) validity of case. This paper proposes notion incremental wh...