VLM-PL: Advanced Pseudo Labeling approach Class Incremental Object Detection with Vision-Language Model

arXiv:2403.05346v1 Announce Type: new
Abstract: In the field of Class Incremental Object Detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenario incremental learning due to their tendency to forget past knowledge. To overcome this, we introduce a new approach called Vision-Language Model assisted Pseudo-Labeling (VLM-PL). This technique uses Vision-Language Model (VLM) to verify the correctness of pseudo ground-truths (GTs) without requiring additional model training. VLM-PL starts by …

abstract advanced arxiv challenge class cs.cv detection humans incremental knowledge labeling language language model learn major object struggle type vision vlm