Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors

CVPR 2022  ·  Yen-Cheng Liu, Chih-Yao Ma, Zsolt Kira ·

With the recent development of Semi-Supervised Object Detection (SS-OD) techniques, object detectors can be improved by using a limited amount of labeled data and abundant unlabeled data. However, there are still two challenges that are not addressed: (1) there is no prior SS-OD work on anchor-free detectors, and (2) prior works are ineffective when pseudo-labeling bounding box regression. In this paper, we present Unbiased Teacher v2, which shows the generalization of SS-OD method to anchor-free detectors and also introduces Listen2Student mechanism for the unsupervised regression loss. Specifically, we first present a study examining the effectiveness of existing SS-OD methods on anchor-free detectors and find that they achieve much lower performance improvements under the semi-supervised setting. We also observe that box selection with centerness and the localization-based labeling used in anchor-free detectors cannot work well under the semi-supervised setting. On the other hand, our Listen2Student mechanism explicitly prevents misleading pseudo-labels in the training of bounding box regression; we specifically develop a novel pseudo-labeling selection mechanism based on the Teacher and Student's relative uncertainties. This idea contributes to favorable improvement in the regression branch in the semi-supervised setting. Our method, which works for both anchor-free and anchor-based methods, consistently performs favorably against the state-of-the-art methods in VOC, COCO-standard, and COCO-additional.

PDF Abstract CVPR 2022 PDF CVPR 2022 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semi-Supervised Object Detection COCO 0.5% labeled data Unbiased Teacher v2 mAP 21.26 ± 0.21 # 1
Semi-Supervised Object Detection COCO 10% labeled data Unbiased Teacher v2 mAP 35.08±0.02 # 11
detector FCOS-Res50 # 1
Semi-Supervised Object Detection COCO 1% labeled data Unbiased Teacher v2 mAP 26.07±0.36 # 2
Semi-Supervised Object Detection COCO 2% labeled data Unbiased Teacher v2 mAP 28.37±0.03 # 6
Semi-Supervised Object Detection COCO 5% labeled data Unbiased Teacher v2 mAP 31.85±0.09 # 11


No methods listed for this paper. Add relevant methods here