Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes

TL;DR

This paper introduces a sampling-based semi-weakly supervised object detection method that generates pseudo-ground-truth boxes online, reducing training complexity and achieving state-of-the-art results with minimal fully-labeled data.

Contribution

A novel sampling strategy for pseudo-ground-truth generation that simplifies training and enhances detection performance with limited fully-labeled images.

Findings

Improves detection performance by 5% on Pascal VOC datasets.

Achieves over 10% mAP increase with only 5-10% fully annotated images.

Eliminates multi-stage training and student-teacher configurations.

Abstract

Semi- and weakly-supervised learning have recently attracted considerable attention in the object detection literature since they can alleviate the cost of annotation needed to successfully train deep learning models. State-of-art approaches for semi-supervised learning rely on student-teacher models trained using a multi-stage process, and considerable data augmentation. Custom networks have been developed for the weakly-supervised setting, making it difficult to adapt to different detectors. In this paper, a weakly semi-supervised training method is introduced that reduces these training challenges, yet achieves state-of-the-art performance by leveraging only a small fraction of fully-labeled images with information in weakly-labeled images. In particular, our generic sampling-based learning strategy produces pseudo-ground-truth (GT) bounding box annotations in an online fashion, eliminating the need for multi-stage training, and student-teacher network configurations. These pseudo GT boxes are sampled from weakly-labeled images based on the categorical score of object proposals accumulated via a score propagation process. Empirical results on the Pascal VOC dataset, indicate that the proposed approach improves performance by 5.0% when using VOC 2007 as fully-labeled, and VOC 2012 as weak-labeled data. Also, with 5-10% fully annotated images, we observed an improvement of more than 10% in mAP, showing that a modest investment in image-level annotation, can substantially improve detection performance.