Solving Missing-Annotation Object Detection with Background Recalibration Loss

View Researcher's Other Codes

Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).

Please contact us in case of a broken link from here

Authors Marios Savvides, Chenchen Zhu, Han Zhang, Qiqi Hao, Fangyi Chen, Zhiqiang Shen
Journal/Conference Name ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Paper Category
Paper Abstract This paper focuses on a novel and challenging detection scenario A majority of true objects/instances is unlabeled in the datasets, so these missing-labeled areas will be regarded as the background during training. Previous art on this problem has proposed to use soft sampling to re-weight the gradients of RoIs based on the overlaps with positive instances, while their method is mainly based on the two-stage detector (i.e. Faster RCNN) which is more robust and friendly for the missing label scenario. In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image. Our design is built on the one-stage detector which is faster and lighter. Inspired by the Focal Loss formulation, we make several significant modifications to fit on the missing-annotation circumstance. We conduct extensive experiments on the curated PASCAL VOC and MS COCO datasets. The results demonstrate that our proposed method outperforms the baseline and other state-of-the-arts by a large margin. Code available https//github.com/Dwrety/mmdetection-selective-iou.
Date of publication 2020
Code Programming Language Python
Comment

Copyright Researcher 2022