BriefGPT.xyz
Aug, 2019
LVIS:用于大规模词汇实例分割的数据集
LVIS: A Dataset for Large Vocabulary Instance Segmentation
HTML
PDF
Agrim Gupta, Piotr Dollár, Ross Girshick
TL;DR
介绍了一个新数据集LVIS,包括超过1000个对象类别和约164k幅图像,用于解决目标检测中的少训练样本问题。
Abstract
Progress on
object detection
is enabled by
datasets
that focus the research community's attention on open challenges. This process led us from simple images to complex scenes and from bounding boxes to segmentati
→