Bounding-box deep calibration for high performance face detection

TL;DR

This paper introduces a Bounding-Box Deep Calibration method that improves face detection accuracy by replacing misaligned annotations with model predictions, enhancing precision and recall without extra inference costs.

Contribution

The paper presents a novel calibration technique that addresses annotation misalignment in training data, significantly boosting face detection performance.

Findings

Improves detection precision and recall across multiple models and datasets.

Does not increase inference time or memory usage.

Effective especially for lightweight, real-time face detectors.

Abstract

Modern convolutional neural networks (CNNs)-based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further improvement of detection performance. In this paper, the authors first predict high confidence detection results on the training set itself. Surprisingly, a considerable part of them exist in the same misalignment problem. Then, the authors carefully examine these cases and point out that annotation misalignment is the main reason. Later, a comprehensive discussion is given for the replacement rationality between predicted and annotated bounding-boxes. Finally, the authors propose a novel Bounding-Box Deep Calibration (BDC) method to reasonably replace misaligned annotations with model predicted bounding-boxes and offer calibrated annotations for the training set. Extensive experiments on multiple detectors and two popular benchmark datasets show the effectiveness of BDC on improving models' precision and recall rate, without adding extra inference time and memory consumption. Our simple and effective method provides a general strategy for improving face detection, especially for light-weight detectors in real-time situations.