Aggregate channel features for multi-view face detection

By Binh Yang, Junjie Yan, Zhen Lei, S. Li. IEEE International Joint Conference on Biometrics, 2014

320 citations recorded by the source corpus.

Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can't meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of channel features to the face detection domain, which extends the image channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate channel features, make a full exploration of feature design, and discover a multi-scale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB test-sets, while runs at 42 FPS on VGA images.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2f04ba0f74df046b0080ca78e56898bd4847898b

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

Citations in the corpus

Finding Tiny Faces (2016, background): “Easy Medium Hard ACF[24] 0.659 0.541 0.273 Two-stage CNN[26] 0.681 0.618 0.323 Multiscale Cascade CNN[25] 0.691 0.634 0.345 Faceness[25] 0.713 0.664 0.424 Multitask Cascade CNN[27] 0.848 0.825 0.598 CMS-RCNN[28] 0 [7] and hard-example mining [21] to ameliorate such effects.”
S^3FD: Single Shot Scale-Invariant Face Detector (2017, background): “After that, lots of works have focused on improving the performance with more sophisticated hand-crafted features [25, 28, 53, 60] and more powerful classiﬁers [2, 33].”
PyramidBox: A Context-assisted Single Shot Face Detector (2018, methodology): “Since that, numerous subsequent works [2,3,4,5,6,7] are proposed for improving the cascade detectors.”
SSH: Single Stage Headless Face Detector (2017, background): “Prior to the re-emergence of convolutional neural networks (CNN), different machine learning algorithms were developed to improve face detection performance [29, 39, 10, 11, 18, 2, 31].”
Face Detection using Deep Learning: An Improved Faster RCNN Approach (2017, methodology): “To address the ﬁrst problem, much effort has been devoted to coming up with more complicated features like HOG[13], SIFT, SURF[14] and ACF[15].”
RetinaFace: Single-stage Dense Face Localisation in the Wild (2019, methodology): “Multi-scale Cascade CNN [60], Two-stage CNN [60], ACF-WIDER [58], Faceness-WIDER [59], Multitask Cascade CNN [66], CMS-RCNN [72], LDCF+ [37], HR [23], Face R-CNN [54], ScaleFace [61], SSH [36], SFD [68], Face R-FCN [57], MSCNN [4], FAN [56], Zhu et al .”
Object Detection With Deep Learning: A Review (2018, methodology): “To achieve better bounding results, multi-view representation [181] and 3D proposal network [228] may provide some guidelines to encode depth information with the aid of inertial sensors (accelerometer and gyrometer) [229].”
From Facial Parts Responses to Face Detection: A Deep Learning Approach (2015, methodology): “We compare Faceness-Net against all published methods [37, 23, 3, 35, 18, 20, 17, 28, 40, 13] in the FDDB.”
Convolutional Channel Features (2015, background): “Multiple channel features first showed great performance in pedestrian detec- tion [12], and was later generalized to face detection [50], edge detection [15] and object proposal generation [55].”
WIDER FACE: A Face Detection Benchmark (2015, methodology): “We select VJ [21], ACF [24], DPM [17], and Faceness [28] as baselines.”
Multi-scale Fully Convolutional Network for Face Detection in the Wild (2017, methodology): “On the WIDER FACE dataset, we compare our MS-FCN detector against several state-of-the-art methods: CMS-RCNN [48], Multi-task Cascade CNN [45], Faceness-WIDER [40], Multi-Scale Cascade CNN [41], Two-Stage CNN [41], and ACF-WIDER [39].”
A survey on face detection in the wild: Past, present and future (2015, unknown): “Finally,astate-of-the-artapproachsimilartoHeadHunterwasindependentlyproposedin[105].”
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks (2016, methodology): “To evaluate the performance of our face detection method, we compare our method against the state-of-the-art methods [1], [5], [6], [11], [18], [19], [26]–[29] in FDDB, and the state-of-the-art methods [1], [11], [24] in WIDER FACE.”
A convolutional neural network cascade for face detection (2015, methodology): “Figure 9: On the FDDB dataset we compare our performance with the state-of-the-art methods including: ACF muItiscale [29], PEP-Adapt [14], Boosted Exemplar [15], HeadHunter [19], Jain et at.”
From Facial Expression Recognition to Interpersonal Relation Prediction (2016, methodology): “Subsequently, we collected images returned from the search engine and run a face detector (Yang et al. 2014) to obtain face regions from these images.”
Deep Learning Face Attributes in the Wild (2014, methodology): “Therefore, multi-view face detectors [30] were developed in Fig.”
Scale-Aware Face Detection (2017, background): “Many works have been proposed to improve the Viola-Jones framework and achieves further improvements, such as local features [41, 20, 36], boosting algorithms [40, 21, 11], cascade structure [2] and multi-pose [22, 17, 12].”