# Confidence Estimation for Object Detection in Document Images

arXiv: https://arxiv.org/abs/2208.13391 · HTML: https://mlsanity.com/paper/2208.13391/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 29 Aug 2022.

## Builds on (most cited first, 10 of 10)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Confidence-Aware Learning for Deep Neural Networks](https://mlsanity.com/paper/2007.01458/) (2020)
- [Active Learning for Deep Object Detection](https://mlsanity.com/paper/1809.09875/) (2018)
- [READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival Documents](https://mlsanity.com/paper/1705.03311/) (2017)
- [HORAE: an annotated dataset of books of hours](https://mlsanity.com/paper/2012.00351/) (2020)
- [Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks](https://mlsanity.com/paper/2012.14163/) (2020)
- [Robust Text Line Detection in Historical Documents: Learning and Evaluation Methods](https://mlsanity.com/paper/2203.12346/) (2022)
- [PageNet: Page Boundary Extraction in Historical Handwritten Documents](https://mlsanity.com/paper/1709.01618/) (2017)

## Abstract (arXiv)

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.