Bounding-box deep calibration for high performance face detection
This work addresses a key limitation in face detection for real-time applications, particularly benefiting light-weight detectors, though it is incremental as it builds on existing CNN-based methods.
The authors tackled the problem of misaligned face detection results with high confidence but low localization accuracy by identifying annotation misalignment as the main cause and proposing a Bounding-Box Deep Calibration method to replace misaligned annotations with model predictions. Experiments on multiple detectors and datasets showed improved precision and recall rates without extra inference time or memory consumption.
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.