Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation

arXiv:2404.08603v1 Announce Type: new
Abstract: Open-vocabulary object detection (OVOD) aims at localizing and recognizing visual objects from novel classes unseen at the training time. Whereas, empirical studies reveal that advanced detectors generally assign lower scores to those novel instances, which are inadvertently suppressed during inference by commonly adopted greedy strategies like Non-Maximum Suppression (NMS), leading to sub-optimal detection performance for novel classes. This paper systematically investigates this problem with the commonly-adopted two-stage OVOD paradigm. Specifically, in the region-proposal stage, proposals …

abstract advanced aggregation arxiv boost confidence cs.cv detection detectors free inference instances novel object objects strategies studies training type visual