Confidence Estimation for Object Detection in Document Images

Mélodie Boillet

doi:10.1016/j.patrec.2022.12.024

Confidence Estimation for Object Detection in Document Images

2023-02-01

5

OA

AI

M

Mélodie Boillet *

C

Christopher Kermorvant

T

Thierry Paquet

DOI：10.1016/j.patrec.2022.12.024

原文链接

查看原文

摘要

En 中文

Deep neural networks are becoming increasingly powerful and large and always require more labelled data to be trained. However, since annotating data is time-consuming, it is now necessary to develop systems that show good performance while learning on a limited amount of data. These data must be correctly chosen to obtain models that are still efficient. For this, the systems must be able to determine which data should be annotated to achieve the best results. In this paper, we propose four estimators to estimate the confidence of object detection predictions. The first two are based on Monte Carlo dropout, the third one on descriptive statistics and the last one on the detector posterior probabilities. In the active learning framework, the three first estimators show a significant improvement in performance for the detection of document physical pages and text lines compared to a random selection of images. We also show that the proposed estimator based on descriptive statistics can replace MC dropout, reducing the computational cost without compromising the performances.(c) 2023 Elsevier B.V. All rights reserved.

Keyword:

Confidence estimation

Document object detection

Active learning

Confidence Estimation for Object Detection in Document Images

摘要

AI总结

期刊

机构

引用论文