Solving Missing-Annotation Object Detection with Background Recalibration Loss

By Han Zhang, Fangyi Chen, Zhiqiang Shen, Qiqi Hao, Chenchen Zhu, Marios Savvides. 2020

61 citations recorded by the source corpus.

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 [1] 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 [2] formulation, we make several significant modifications to fit on the missing-annotation circumstance. We conduct extensive experiments on the curated PASCAL VOC [3] and MS COCO [4] datasets. The results demonstrate that our proposed method outperforms the baseline and other state-of-the-arts by a large margin.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiang Bai
2. Guisong Xia
3. Jiebo Luo
4. Jian Ding
5. Serge J. Belongie
6. Nan Xue
7. Wen Yang
8. Tianfang Zhao

In Computer Vision and Pattern Recognition

1. Guisong Xia
2. Xiang Bai
3. Jiebo Luo
4. Luc Van Gool
5. Junwei Han
6. Dacheng Tao
7. Jian Ding
8. Mingkun Yang

Citations in the corpus

• EPicker is an exemplar-based continual learning approach for knowledge accumulation in cryoEM particle picking (2022, methodology): “Some previous works dealing with sparse annotation in natural images solved this problem by reweighting the importance of region proposals generated by the two-stage object detector Faster RCNN 38,39 or recalibrating the loss of the anchors used by the one-stage object detector YOLO 40 .”
• Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, result): “However, if the researchers want to study this problem and further improve the performance, we recommend researchers refer to these prior works [77], [78].”