BriefGPT.xyz
Sep, 2018
深度目标检测主动学习
Active Learning for Deep Object Detection
HTML
PDF
Clemens-Alexander Brust, Christoph Käding, Joachim Denzler
TL;DR
本研究结合活性学习和增量学习的方法，提出一种基于不确定度的适用于大多数对象检测器的主动学习度量标准，并探讨在样本选择过程中如何解决类别不平衡问题，通过系统评估在PASCAL VOC 2012数据集上，实现对新未标注数据集的持续探索。
Abstract
The great success that
deep models
have achieved in the past is mainly owed to large amounts of
labeled training data
. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both
→