论文标题
密集的老师：半监督对象检测的密集伪标签
Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection
论文作者
论文摘要
迄今为止，最强大的半监督对象检测器（SS-OD）基于伪盒，该盒子需要一系列具有微调超参数的后处理。在这项工作中，我们建议用稀疏的伪盒代替稀疏的伪盒，作为伪标签的一种团结而直接的形式。与伪盒相比，我们的密集伪标签（DPL）不涉及任何后处理方法，因此保留了更丰富的信息。我们还引入了一种区域选择技术，以突出关键信息，同时抑制密集标签所携带的噪声。我们将利用DPL作为密集老师的拟议的SS-OD算法命名。在可可和VOC上，密集的老师与基于伪盒的方法相比，在各种设置下表现出卓越的表现。
To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the dense prediction as a united and straightforward form of pseudo-label. Compared to the pseudo-boxes, our Dense Pseudo-Label (DPL) does not involve any post-processing method, thus retaining richer information. We also introduce a region selection technique to highlight the key information while suppressing the noise carried by dense labels. We name our proposed SS-OD algorithm that leverages the DPL as Dense Teacher. On COCO and VOC, Dense Teacher shows superior performance under various settings compared with the pseudo-box-based methods.
