Bounding-box deep calibration for high performance face detection
arXiv:2110.03892 · doi:10.1049/cvi2.12122
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.
arXiv comment12 pages, 7 figures, 5 tables, 1 algorithm, 9 equation, 2 definition
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- SSD: Single Shot MultiBox Detector
- Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
- Squeeze-and-Excitation Networks
- UnitBox: An Advanced Object Detection Network
- Deep Label Distribution Learning with Label Ambiguity
- TinaFace: Strong but Simple Baseline for Face Detection
- SFA: Small Faces Attention Face Detector
- CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection