KPNet: Towards Minimal Face Detector
arXiv:2003.07543
Abstract
The small receptive field and capacity of minimal neural networks limit their performance when using them to be the backbone of detectors. In this work, we find that the appearance feature of a generic face is discriminative enough for a tiny and shallow neural network to verify from the background. And the essential barriers behind us are 1) the vague definition of the face bounding box and 2) tricky design of anchor-boxes or receptive field. Unlike most top-down methods for joint face detection and alignment, the proposed KPNet detects small facial keypoints instead of the whole face by in a bottom-up manner. It first predicts the facial landmarks from a low-resolution image via the well-designed fine-grained scale approximation and scale adaptive soft-argmax operator. Finally, the precise face bounding boxes, no matter how we define it, can be inferred from the keypoints. Without any complex head architecture or meticulous network designing, the KPNet achieves state-of-the-art accuracy on generic face detection and alignment benchmarks with only parameters, which runs at 1000fps on GPU and is easy to perform real-time on most modern front-end chips.
arXiv commentAAAI 2020
References in corpus (20)
- UnitBox: An Advanced Object Detection Network
- Associative Embedding: End-to-End Learning for Joint Detection and Grouping
- Stacked Hourglass Networks for Human Pose Estimation
- Feature Pyramid Networks for Object Detection
- Human Pose Regression by Combining Indirect Part Detection and Contextual Information
- CornerNet: Detecting Objects as Paired Keypoints
- Face Detection through Scale-Friendly Deep Convolutional Networks
- From Facial Parts Responses to Face Detection: A Deep Learning Approach
- Detecting Faces Using Region-based Fully Convolutional Networks
- Style Aggregated Network for Facial Landmark Detection
- PyramidBox: A Context-assisted Single Shot Face Detector
- Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
- PFLD: A Practical Facial Landmark Detector
- Joint Multi-view Face Alignment in the Wild
- Scale-Aware Face Detection
- Feature Agglomeration Networks for Single Stage Face Detection
- Crafting GBD-Net for Object Detection
- Selective Refinement Network for High Performance Face Detection
- Supervised Transformer Network for Efficient Face Detection
- Face R-CNN