DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection

arXiv:2310.01393v3 Announce Type: replace
Abstract: Open-vocabulary object detection (OVOD) aims to detect the objects beyond the set of classes observed during training. This work introduces a straightforward and efficient strategy that utilizes pre-trained vision-language models (VLM), like CLIP, to identify potential novel classes through zero-shot classification. Previous methods use a class-agnostic region proposal network to detect object proposals and consider the proposals that do not match the ground truth as background. Unlike these methods, our method will select a subset …

arxiv cs.cv detection dynamic object self-training simple training type