Face Detection On Wider Face Hard

Metrics

Results

Performance results of various models on this benchmark

Model Name	AP	Paper Title	Repository
img2pose	0.839	img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation	-
MogFace (HCAM)	0.874	MogFace: Towards a Deeper Appreciation on Face Detection	-
DupNet-L+PACT	0.906	DupNet: Towards Very Tiny Quantized CNN with Improved Accuracy for Face Detection	-
FDNet	0.896	Face Detection Using Improved Faster RCNN	-
AInnoFace	0.912	Accurate Face Detection for High Performance	-
MogFace (Ali-AMS)	0.873	MogFace: Towards a Deeper Appreciation on Face Detection	-
+ DH + HIM	0.897	Robust Face Detection via Learning Small Faces on Hard Images	-
Face R-FCN	0.876	Detecting Faces Using Region-based Fully Convolutional Networks	-
RetinaFace+Lpts+Lpixel	0.91857	RetinaFace: Single-stage Dense Face Localisation in the Wild	-
WSMA-Seg	0.8723	Segmentation is All You Need	-
FD-CNN	0.51	Fast Deep Convolutional Face Detection in the Wild Exploiting Hard Sample Mining	-
Poly-NL(ResNet-50)	0.9276	Poly-NL: Linear Complexity Non-local Layers with Polynomials	-
Two-stage CNN	0.304	WIDER FACE: A Face Detection Benchmark	-
PyramidBox	0.889	PyramidBox: A Context-assisted Single Shot Face Detector	-
Multiscale Cascade CNN	0.400	WIDER FACE: A Face Detection Benchmark	-
RNNPool-Face-C	0.70	RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference	-
ASFD-D6	0.925	ASFD: Automatic and Scalable Face Detector	-
SCRFD-34GF	0.8529	Sample and Computation Redistribution for Efficient Face Detection	-
YOLOv5s	0.828	YOLO5Face: Why Reinventing a Face Detector	-
MSCNN	0.809	A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection	-

0 of 40 row(s) selected.