Conceptos Básicos
MultIOD is a class-incremental object detector based on CenterNet, focusing on rehearsal-free and anchor-free object detection.
Estadísticas
대부분의 기존 CIOD 모델은 Faster-RCNN에 기반을 두고 있음.
MultIOD는 CenterNet 알고리즘을 기반으로 함.
EfficientNet-B3 모델은 파라미터 수를 줄이면서 성능을 향상시킴.
Citas
"We argue that more effort should be dedicated to anchor-free and rehearsal-free object detection."
"Results show that our method outperforms a range of state-of-the-art methods on two Pascal VOC datasets."