The classification and regression head are both indispensable components to build up a dense object detector, which are usually supervised by the same training samples and thus expected to have consistency with each other for detecting objects accurately in the detection pipeline. In this paper, we break the convention of the same training samples for these two heads in dense detectors and explore a novel supervisory paradigm, termed as Mutual Supervision (MuSu), to respectively and mutually assign training samples for the classification and regression head to ensure this consistency. MuSu defines training samples for the regression head mainly based on classification predicting scores and in turn, defines samples for the classification head based on localization scores from the regression head. Experimental results show that the convergence of detectors trained by this mutual supervision is guaranteed and the effectiveness of the proposed method is verified on the challenging MS COCO benchmark. We also find that tiling more anchors at the same location benefits detectors and leads to further improvements under this training scheme. We hope this work can inspire further researches on the interaction of the classification and regression task in detection and the supervision paradigm for detectors, especially separately for these two heads.
翻译:分类和回归头部是建立密度物体探测器的不可或缺的组成部分,通常由同样的训练样品加以监督,因此,在探测管道中准确探测物体时,预期彼此会相互一致。在本文件中,我们打破了对这两个头进行密集探测器的相同训练样品的公约,并探索了一个新的监督模式,称为相互监督(Musu),分别和相互分配分类和回归头部的培训样品,以确保这种一致性。Musu主要根据预测分数的分类确定回归头部的培训样品,并反过来根据从回归头部得出的地方化分数确定分类头部的样品。实验结果显示,通过这种相互监督所培训的探测器的趋同得到保证,拟议方法的效力在具有挑战性的MS COCO基准上得到核实。我们还发现,在同一地点加固更多的锚有利于探测器,并导致在培训计划下进一步改进。我们希望这项工作能够激发进一步研究在检测和检测监督模式方面,特别是针对这两个头的分类和回归任务之间的相互作用。