BriefGPT.xyz
Apr, 2024
无需训练的自信度聚合增益对开放词汇物体检测的改进
Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation
HTML
PDF
Yanhao Zheng, Kai Liu
TL;DR
研究着重探讨开放词汇对象检测 (OVOD) 中的问题,包括对新类别的检测性能不佳以及候选区域和对象分类阶段的局限性,并提出了一种后处理方案(AggDet),通过两种先进的衡量方法来调整信心分数和恢复误判的对象,并在OV-COCO和OV-LVIS基准上取得了显著的性能提升。
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
→