Confidence Estimation for Object Detection in Document Images
This work addresses the challenge of reducing annotation costs for document image analysis, though it is incremental as it builds on existing active learning and confidence estimation methods.
The paper tackles the problem of selecting which data to annotate for training object detection models with limited labeled data by proposing four confidence estimators for predictions, with three showing significant performance improvements in active learning for document page and text line detection compared to random selection.
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.