Continual Detection Transformer for Incremental Object Detection

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 23799 - 23808
• Main Authors: Liu, Yaoyao, Schiele, Bernt, Vedaldi, Andrea, Rupprecht, Christian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2023
• Subjects: continual; Detectors; Focusing; low-shot; meta; Object detection; or long-tail learning; Predictive models; Protocols; Training; Transfer; Transformers

Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to catastrophic forgetting, which is often addressed by techniques such as knowledge distillation (KD) and exem-plar replay (E...