Face Detection with the Faster R-CNN

By Huaizu Jiang, Eric Learned-Miller. IEEE International Conference on Automatic Face & Gesture Recognition, 2016

732 citations recorded by the source corpus.

While deep learning based methods for generic object detection have improved rapidly in the last two years, most approaches to face detection are still based on the R-CNN framework [11], leading to limited accuracy and processing speed. In this paper, we investigate applying the Faster RCNN [26], which has recently demonstrated impressive results on various object detection benchmarks, to face detection. By training a Faster R-CNN model on the large scale WIDER face dataset [34], we report state-of-the-art results on the WIDER test set as well as two other widely used face detection benchmarks, FDDB and the recently released IJB-A.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/d13101cbb8ca0abb8aec0bacc5013df4b6a378cf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Unsupervised Hard Example Mining from Videos for Improved Object Detection (2018, methodology): “Many of these object detectors have been re-purposed for other tasks such as face detection [39,29,60,15], [31,63,62,25,57,23,66] and pedestrian detection [64,14,6,7,22,30,65], achieving impressive results [24,61,12].”
Multi-scale Fully Convolutional Network for Face Detection in the Wild (2017, methodology): “On the FDDB dataset, we compare our MS-FCN detector against many state-of-the-art methods: Xiaomi [34], STN [3], UnitBox [42], Conv3D [20], Faster RCNN [14], Hyperface [26], MTCNN [45], Faceness [40], DDFD [6], CascadeCNN [18], Yan et al.”
Finding Tiny Faces in the Wild with Generative Adversarial Network (2018, methodology): “Inspired by the great success of Faster RCNN, several recent works [14, 25, 37] utilized this framework to detect faces and showed impressive performance on the FDDB benchmark [13].”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, unknown): “1) Baseline Composition: We test four state-of-the-art deep face detectors: (1) Dual Shot Face Detector ( DSFD ) [147] 10 ; (2) Pyramidbox [148] 11 ; (3) Single Stage Headless Face Detector ( SSH ) [149] 12 ; (4) Faster RCNN [150].”
Fine-Grained Head Pose Estimation Without Keypoints (2017, methodology): “For BIWI we run a Faster R-CNN [21] face detector trained on the WIDER Face Dataset [31], [8] and deployed in a Docker container [23].”
Face Detection using Deep Learning: An Improved Faster RCNN Approach (2017, methodology): “One of very important and highly successful framework for generic object detection is the region-based CNN (RCNN) method [9] , which is a kind of CNN extension for solving the object detection tasks.”
A graph-based CNN-LSTM stock price prediction algorithm with leading indicators (2021, methodology): “It has successfully been applied in various fields such as detection [46] and segmentation [47].”
S^3FD: Single Shot Scale-Invariant Face Detector (2017, methodology): “Finally, we evaluate our face detector on FDDB against the state-of-the-art methods [1, 6, 7, 15, 18, 19, 20, 22, 24, 25, 31, 35, 36, 43, 47, 49, 55, 57, 58].”
An All-In-One Convolutional Neural Network for Face Analysis (2016, methodology): “Recent methods for face detection based on deep CNNs such as DP2MFD [35], Faceness [50], Hyperface [36], Faster-RCNN [20], etc., have signiﬁcantly outperformed traditional approaches like TSM [59] and NDPFace [30].”
Multi-task Generative Adversarial Network for Detecting Small Objects in the Wild (2020, methodology): “To overcome the problem of detecting small faces, traditional methods (Jiang and Learned-Miller 2017; Wan et al. 2016; Zhu et al. 2017a) re-size input images to different scales during training and testing, which inevitably increases the GPU memory and computation costs.”
Detecting small faces in the wild based on generative adversarial network and contextual information (2019, methodology): “Existing face detection methods can be broadly categorized as handcrafted feature based methods [16–19] and CNN-based methods [10,11,20–23] .”
Face Recognition Algorithm Bias: Performance Differences on Images of Children and Adults (2019, methodology): “The open-source algorithm uses a face detector based on Faster R-CNN [9] [14] and feature extractor based on the VGG-Face [12].”
Adversarial Examples that Fool Detectors (2017, unknown): “[12] that can generalize across view conditions.”
Object Detection With Deep Learning: A Review (2018, background): “representative models and their different characteristics in several application domains, including generic object detection [15], [16], [18], salient object detection [27], [28], face detection [29]–[31] and pedestrian detection [32], [33].”