Humble Teachers Teach Better Students for Semi-Supervised Object Detection
share
We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework. Our method is featured with 1) the exponential moving averaging strategy to update the teacher from the student online, 2) using plenty of region proposals and soft pseudo-labels as the student's training targets, and 3) a light-weighted detection-specific data ensemble for the teacher to generate more reliable pseudo-labels. Compared to the recent state-of-the-art – STAC, which uses hard labels on sparsely selected hard pseudo samples, the teacher in our model exposes richer information to the student with soft-labels on many proposals. Our model achieves COCO-style AP of 53.04 using VOC12 as unlabeled data. On MS-COCO, it outperforms prior work when only a small percentage of data is taken as labeled. It also reaches 53.8 MS-COCO test-dev with 3.1 R-CNN, by tapping into unlabeled data of a similar size to the labeled data.
READ FULL TEXT