computer-vision-5

Occluded Face Detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in occluded-face-detection-5

Trend

Dataset

Best Model

Actions

MAFA

Libraries

i

Use these libraries to find occluded-face-detection-5 models and implementations

Datasets

OCFR-LFW

HEADSET

Subtasks

No subtasks available.

Most implemented papers

Occlusion Coherence: Detecting and Localizing Occluded Faces

Charless C. Fowlkes, Golnaz Ghiasi•Sat Jun 27 2015

A hierarchical deformable part model for face detection and landmark localization that explicitly models part occlusion is described that yields a detection system that outperforms existing approaches for occluded instances while maintaining competitive accuracy in detection and landmarks localization for unoccluded instances.

74

Content

0

Paper Graph

DSFD: Dual Shot Face Detector

Ying Tai, Jian Yang, Feiyue Huang, Jilin Li, Jian Li, Yabiao Wang, Changan Wang, J. Qian, Chengjie Wang•Tue Oct 23 2018

A novel detection network named Dual Shot face Detector (DSFD) is proposed which inherits the architecture of SSD and introduces a Feature Enhance Module (FEM) for transferring the original feature maps to extend the single shot detector to dual shot detector.

458 0

Paper Graph

Adversarial Occlusion-aware Face Detection

R. He, Yujia Chen, Lingxiao Song, Yibo Hu•Thu Sep 14 2017

Occluded face detection is a challenging detection task due to the large appearance variations incurred by various real-world occlusions. This paper introduces an Adversarial Occlusion-aware Face Detector (AOFD) by simultaneously detecting occluded faces and segmenting occluded areas. Specifically, we employ an adversarial training strategy to generate occlusion-like face features that are difficult for a face detector to recognize. Occlusion is predicted simultaneously while detecting occluded faces and the occluded area is utilized as an auxiliary instead of being regarded as a hindrance. Moreover, the supervisory signals from the segmentation branch will reversely affect the features, helping extract more informative features. Consequently, AOFD is able to find the faces with few exposed facial landmarks with very high confidences and keeps high detection accuracy even for masked faces. Extensive experiments demonstrate that AOFD not only significantly outperforms state-of-the-art methods on the MAFA occluded face detection dataset, but also achieves competitive detection accuracy on benchmark dataset for general face detection such as FDDB.

33 0

Paper Graph

Face Attention Network: An Effective Face Detector for the Occluded Faces

Gang Yu, Ye Yuan, Jianfeng Wang•Sun Nov 19 2017

A novel face detector called Face Attention Network (FAN), which can significantly improve the recall of the face detection problem in the occluded case without compromising the speed, and is integrated with the anchor assign strategy and data augmentation techniques.

159 0

Paper Graph

Adding a benchmark result helps the community track progress.