MSFD:Multi-Scale Receptive Field Face Detector
This work addresses the problem of detecting faces at different scales for computer vision applications, representing an incremental improvement with specific gains in speed and accuracy.
The paper tackles face detection across varied scales by proposing MSFD, a multi-scale receptive field detector that achieves superior performance on FDDB, Pascal-Faces, and WIDER FACE datasets while running at 31 FPS on GPU for VGA-resolution images.
We aim to study the multi-scale receptive fields of a single convolutional neural network to detect faces of varied scales. This paper presents our Multi-Scale Receptive Field Face Detector (MSFD), which has superior performance on detecting faces at different scales and enjoys real-time inference speed. MSFD agglomerates context and texture by hierarchical structure. More additional information and rich receptive field bring significant improvement but generate marginal time consumption. We simultaneously propose an anchor assignment strategy which can cover faces with a wide range of scales to improve the recall rate of small faces and rotated faces. To reduce the false positive rate, we train our detector with focal loss which keeps the easy samples from overwhelming. As a result, MSFD reaches superior results on the FDDB, Pascal-Faces and WIDER FACE datasets, and can run at 31 FPS on GPU for VGA-resolution images.