S$^3$FD: Single Shot Scale-invariant Face Detector
It improves face detection accuracy, especially for small faces, which is crucial for applications like surveillance and photography, but it is incremental as it builds on existing anchor-based methods.
The paper tackles the problem of anchor-based face detectors performing poorly on small faces by introducing a scale-invariant framework, achieving state-of-the-art performance on benchmarks like AFW, PASCAL face, FDDB, and WIDER FACE, with a speed of 36 FPS on a Titan X GPU.
This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S$^3$FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces. Specifically, we try to solve the common problem that anchor-based detectors deteriorate dramatically as the objects become smaller. We make contributions in the following three aspects: 1) proposing a scale-equitable face detection framework to handle different scales of faces well. We tile anchors on a wide range of layers to ensure that all scales of faces have enough features for detection. Besides, we design anchor scales based on the effective receptive field and a proposed equal proportion interval principle; 2) improving the recall rate of small faces by a scale compensation anchor matching strategy; 3) reducing the false positive rate of small faces via a max-out background label. As a consequence, our method achieves state-of-the-art detection performance on all the common face detection benchmarks, including the AFW, PASCAL face, FDDB and WIDER FACE datasets, and can run at 36 FPS on a Nvidia Titan X (Pascal) for VGA-resolution images.