TL;DR通过在目标检测方案的样本权重分析中,提出了 Prime Sample Attention,即在训练过程中重点关注重要的样本,相较于传统随机采样和硬样本挖掘方法,可以有效提高检测器性能。
Abstract
It is a common paradigm in object detection frameworks to treat all samples
equally and target at maximizing the performance on average. In this work, we
revisit this paradigm through a careful study on how diffe