Face Detection using Deep Learning: An Improved Faster RCNN Approach

Sun, Xudong; Wu, Pengcheng; Hoi, Steven C. H.

doi:10.48550/arxiv.1701.08289

Cited by 22 publications

(26 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The result is obviously higher than HR-ER [78] and Conv3D [79], and comparable with the best academic face detectors, e.g. STN [9], Xiaomi [80], and DeepIR [81]. After investigating our false positives, we surprisingly find some tiny regions (shown in Figure 16(b)) that can hardly be removed by our method, since they have very similar appearance and structure of the face, and may only be resolved by contextbased model.…”

Section: E Face Detectionsupporting

confidence: 60%

Joint Multi-View Face Alignment in the Wild

Deng

Trigeorgis

Zhou

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

The de facto algorithm for facial landmark estimation involves running a face detector with a subsequent deformable model fitting on the bounding box. This encompasses two basic problems: i) the detection and deformable fitting steps are performed independently, while the detector might not provide best-suited initialisation for the fitting step, ii) the face appearance varies hugely across different poses, which makes the deformable face fitting very challenging and thus distinct models have to be used (e.g., one for profile and one for frontal faces). In this work, we propose the first, to the best of our knowledge, joint multi-view convolutional network to handle large pose variations across faces in-the-wild, and elegantly bridge face detection and facial landmark localisation tasks. Existing joint face detection and landmark localisation methods focus only on a very small set of landmarks. By contrast, our method can detect and align a large number of landmarks for semi-frontal (68 landmarks) and profile (39 landmarks) faces. We evaluate our model on a plethora of datasets including standard static image datasets such as IBUG, 300W, COFW, and the latest Menpo Benchmark for both semi-frontal and profile faces. Significant improvement over state-of-the-art methods on deformable face tracking is witnessed on 300VW benchmark. We also demonstrate state-ofthe-art results for face detection on FDDB and MALF datasets.Index Terms-Joint multi-view face alignment, Cascade face detection

show abstract

Section: E Face Detectionsupporting

confidence: 60%

Joint Multi-View Face Alignment in the Wild

Deng

Trigeorgis

Zhou

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…STN [3] proposes a new supervised transformer network and a ROI convolution with RPN for face detection. Sun et al [43] presents several effective strategies to improve Faster RCNN for resolving face detection tasks. In this paper, inspired by the RPN in Faster RCNN [38] and the multi-scale mechanism in SSD [26], we develop a state-ofthe-art face detector with real-time speed.…”

Section: Related Workmentioning

confidence: 99%

“…Hence, we manually review the results and add 238 unlabelled faces (annotations will be released later and some examples are shown in the supplementary materials). 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]. The results are shown in Fig.…”

Section: Evaluation On Benchmarkmentioning

confidence: 99%

“…On the one hand, many works [21,31,54,55,58] have applied CNN as the feature extractor in the traditional face detection framewrok. On the other hand, face detection is regarded as a special case of generic object detection and lots of methods [3,15,43,49,59] have inherited valid techniques from generic object detection method [38]. Following the latter route, we improve the anchor-based generic object detection frameworks and propose a state-of-the-art face detector.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

S^3FD: Single Shot Scale-Invariant Face Detector

Zhang

Zhu

Lei

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

473

547

View full text Add to dashboard Cite

This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S 3 FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces. Specifically, we try to solve the common problem that anchorbased detectors deteriorate dramatically as the objects become smaller. We make contributions in the following three aspects: 1) proposing a scale-equitable face detection framework to handle different scales of faces well. We tile anchors on a wide range of layers to ensure that all scales of faces have enough features for detection. Besides, we design anchor scales based on the effective receptive field and a proposed equal proportion interval principle; 2) improving the recall rate of small faces by a scale compensation anchor matching strategy; 3) reducing the false positive rate of small faces via a max-out background label. As a consequence, our method achieves state-of-theart detection performance on all the common face detection benchmarks, including the AFW, PASCAL face, FDDB and WIDER FACE datasets, and can run at 36 FPS on a Nvidia Titan X (Pascal) for VGA-resolution images.

show abstract

“…We conduct face detection experiments on three benchmark datasets FDDB, AFW and MALF and we compared with all public methods [8,21,36,7,14,38,26,1,11,29,19,42,40] and so on. We regress the annotation with 5 facial points according to Eq.…”

Section: Comparing With State-of-the-artmentioning

confidence: 99%

Beyond Trade-Off: Accelerate FCN-Based Face Detector with Higher Accuracy

Song

Liu

Jiang

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Fully convolutional neural network (FCN) has been dominating the game of face detection task for a few years with its congenital capability of sliding-window-searching with shared kernels, which boiled down all the redundant calculation, and most recent state-of-the-art methods such as Faster-RCNN, SSD, YOLO and FPN use FCN as their backbone. So here comes one question: Can we find a universal strategy to further accelerate FCN with higher accuracy, so could accelerate all the recent FCN-based methods? To analyze this, we decompose the face searching space into two orthogonal directions, 'scale' and 'spatial'. Only a few coordinates in the space expanded by the two base vectors indicate foreground. So if FCN could ignore most of the other points, the searching space and false alarm should be significantly boiled down. Based on this philosophy, a novel method named scale estimation and spatial attention proposal (S 2 AP ) is proposed to pay attention to some specific scales and valid locations in image pyramid. Furthermore, we adopt a masked-convolution operation based on the attention result to accelerate FCN calculation. Experiments show that FCN-based method RPN can be accelerated by about 4× with the help of S 2 AP and masked-FCN and at the same time it can also achieve the state-of-the-art on FDDB, AFW and MALF face detection benchmarks as well.

show abstract

Face Detection using Deep Learning: An Improved Faster RCNN Approach

Cited by 22 publications

References 22 publications

Joint Multi-View Face Alignment in the Wild

Joint Multi-View Face Alignment in the Wild

S^3FD: Single Shot Scale-Invariant Face Detector

Beyond Trade-Off: Accelerate FCN-Based Face Detector with Higher Accuracy

Contact Info

Product

Resources

About