A Simple Semi-Supervised Learning Framework for Object Detection

TL;DR

This paper introduces STAC, a simple semi-supervised learning framework for object detection that leverages pseudo labels and strong data augmentation to improve performance with limited labeled data.

Contribution

The paper presents a novel semi-supervised object detection framework, STAC, combining pseudo labeling and strong augmentation, demonstrating significant improvements over supervised baselines.

Findings

STAC improves AP^0.5 on VOC07 from 76.30 to 79.08.

On MS-COCO, STAC achieves 24.38 mAP with only 5% labeled data.

STAC demonstrates 2x higher data efficiency compared to supervised methods.

Abstract

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/.