Learning Causal Features for Incremental Object Detection

arXiv:2403.00591v1 Announce Type: new
Abstract: Object detection limits its recognizable categories during the training phase, in which it can not cover all objects of interest for users. To satisfy the practical necessity, the incremental learning ability of the detector becomes a critical factor for real-world applications. Unfortunately, neural networks unavoidably meet catastrophic forgetting problem when it is implemented on a new task. To this end, many incremental object detection models preserve the knowledge of previous tasks by replaying samples or …

abstract applications arxiv catastrophic forgetting cs.cv detection features incremental networks neural networks objects practical training type world