Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer

TL;DR

This paper introduces a progressive knowledge transfer framework that leverages an external fully-annotated dataset to significantly improve weakly supervised object detection accuracy, achieving state-of-the-art results.

Contribution

It proposes an iterative knowledge transfer method using a one-class universal detector to enhance weakly supervised detection with non-overlapping source datasets.

Findings

Achieved 59.7% mAP on Pascal VOC 2007

Improved detection performance after retraining with pseudo ground truths

Set new state-of-the-art in weakly supervised object detection with knowledge transfer

Abstract

In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain. This setting is of great practical value due to the existence of many off-the-shelf detection datasets. To more effectively utilize the source dataset, we propose to iteratively transfer the knowledge from the source domain by a one-class universal detector and learn the target-domain detector. The box-level pseudo ground truths mined by the target-domain detector in each iteration effectively improve the one-class universal detector. Therefore, the knowledge in the source dataset is more thoroughly exploited and leveraged. Extensive experiments are conducted with Pascal VOC 2007 as the target weakly-annotated dataset and COCO/ImageNet as the source fully-annotated dataset. With the proposed solution, we achieved an mAP of $59.7\%$ detection performance on the VOC test set and an mAP of $60.2\%$ after retraining a fully supervised Faster RCNN with the mined pseudo ground truths. This is significantly better than any previously known results in related literature and sets a new state-of-the-art of weakly supervised object detection under the knowledge transfer setting. Code: \url{https://github.com/mikuhatsune/wsod_transfer}.