A Simple Semi-Supervised Learning Framework for Object Detection

10 May 2020  ·  Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li, Han Zhang, Chen-Yu Lee, Tomas Pfister ·

Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data. Although there has been remarkable recent progress, the scope of demonstration in SSL has mainly been on image classification tasks. In this paper, we propose STAC, a simple yet effective SSL framework for visual object detection along with a data augmentation strategy. STAC deploys highly confident pseudo labels of localized objects from an unlabeled image and updates the model by enforcing consistency via strong augmentations. We propose experimental protocols to evaluate the performance of semi-supervised object detection using MS-COCO and show the efficacy of STAC on both MS-COCO and VOC07. On VOC07, STAC improves the AP$^{0.5}$ from $76.30$ to $79.08$; on MS-COCO, STAC demonstrates $2{\times}$ higher data efficiency by achieving 24.38 mAP using only 5\% labeled data than supervised baseline that marks 23.86\% using 10\% labeled data. The code is available at https://github.com/google-research/ssl_detection/.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semi-Supervised Object Detection COCO 100% labeled data STAC mAP 39.2 # 13
Semi-Supervised Object Detection COCO 10% labeled data STAC mAP 28.64±0.21 # 26
Semi-Supervised Object Detection COCO 1% labeled data STAC mAP 13.97±0.35 # 22
Semi-Supervised Object Detection COCO 2% labeled data STAC mAP 18.25±0.25 # 17
Semi-Supervised Object Detection COCO 5% labeled data STAC mAP 24.38±0.12 # 23