Detecting small faces in the wild based on generative adversarial network and contextual information

Zhang, Yongqiang; Ding, Mingli; Bai, Yancheng; Ghanem, Bernard

doi:10.1016/j.patcog.2019.05.023

Cited by 29 publications

(5 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…C1 C2 C3 C4 C5 C6 C7 Total [Zeng et al 2019] [Zhou et al 2020 1 1 1 1 1 1 1 7 [Liao et al 2016] 1 0.5 1 1 1 1 1 6.5 [Chen et al 2018] [Shi et al 2018] [Zhang et al 2017a] [Zhou et al 2022] [Zhang et al 2020] [Zhu et al 2018] [Zhang et al 2019b 1 1 1 0 1 1 1 6 [Liu and Levine 2017] [Zhang et al 2019a] [Triantafyllidou et al 2018] [Micheal and Geetha 2017] [Li et al 2020] [Jiang et al 2018] [Sawat et al 2020] [Wang et al 2019] 1 1 0.5 0 1 1 1 5.5 [Zheng et al 2016] [Alafif et al 2017] [Deng and Xie 2017b] [Zakaria et al 2018] [Nanni et al 2019] 1 1 0.5 1 0 1 1 5.5 [Deng and Xie 2017a] 1 1 1 0 0.5 1 1 5.5 [Bai and Ghanem 2017] 0.5 1 1 0 1 1 1 5.5 1 0.5 1 0 1 1 1 5.5 [Lin et al 2016] 1 1 1 0 1 0 1 5 [Ge et al 2017] [El-Barkouky et al 2014] 1 1 0.5 0 0.5 1 1 5 [Yan et al 2014] 1 0.5 0.5 0 1 1 1 5 [Nguyen et al 2015b] 0.5 1 1 0 0.5 1 1 5 [Li et al 2017a] 1 1 0.5 0 1 0 1 4.5 [Yang et al 2018] 1 0.5 1 0 0 1 1 4.5 [Shu et al 2017] 0.5 1 0.5 0 0.5 1 1 4.5 [Lv et al 2016] 0.5 1 0.5 0 0.5 1 1 4.5 [Chai et al 2014] 1 0.5 0.5 0 0.5 1 1 4.5 [Marčetić et al 2016] 1 0.5 1 0 0.5 1 0 4 [Li et al ...…”

Section: Referencementioning

confidence: 99%

Detecting faces in specific scenarios: Systematic Literature Review

Dias,

Ivamoto,

Lima

2023

Anais Do XX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2023)

View full text Add to dashboard Cite

Facial detection is a base component for multiple applications in the fields of biometrics, surveillance, human-robot interaction and others. Although significant progress has been made in the field over the past decade, there are still gaps to be addressed, particularly in specific scenarios as the presence of partial occlusion, variations of lighting, pose, and scale among others. This work aims to provide a comprehensive evaluation of recent studies on facial detection in the wild through a systematic literature review. The review includes a focus on the use of scenario-specific information within the field. A total of forty-five papers were analyzed to provide an overview of the field, incorporating information on scenarios.

show abstract

Section: Referencementioning

confidence: 99%

Detecting faces in specific scenarios: Systematic Literature Review

Dias,

Ivamoto,

Lima

2023

Anais Do XX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2023)

View full text Add to dashboard Cite

show abstract

“…Generative Adversarial Network. Recently, GAN [32] have attracted widespread attention [33]- [36]. The essence of GAN is to generate similar distributions through adversarial learning strategy.…”

Section: Related Workmentioning

confidence: 99%

Mars Image Super-Resolution Based on Generative Adversarial Network

Wang

Zhang

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

High-resolution (HR) Mars images have great significance for studying the landform features of Mars and analyzing the climate on Mars. Nowadays, the mainstream image super-resolution methods are based on deep learning or CNNs, which are better than traditional methods. However, these deep learning based methods obtain low-resolution(LR) images usually by using an ideal down-sampling method (e.g. bicubic interpolation). There are two limitations in the existing SR methods: 1) The paired LR-HR data by using such methods has a satisfactory results when tested on an ideal datasets. But, these methods always fail in real Mars image super-resolution, since real Mars images rarely obey an ideal down-sampling rule. 2) The LR images obtained by bicubic interpolation have no noise while real Mars images usually have noise, which leads to the super-resolved images are not realistic in texture details. To solve the above-mentioned problems, in this article, we propose a novel two-step framework. Specifically, to address limitation 1), we focus on designing a new degradation framework by estimating blur-kernels. To address limitation 2), a Generative Adversarial Network (GAN) is trained to generate noise distribution. Extensive experiments on the Mars32k dataset demonstrate the effectiveness of the proposed method, and we achieve better qualitative and quantitative results compared to other SOTA methods.INDEX TERMS Generative Adversarial Network, Kernel estimation , Mars image super-resolutionn, Noise model.

show abstract

“…Recently, with the rapid development of deep learning methods, convolutional neural network (CNN) based algorithms [19][20][21][22][23][24][25] have demonstrated amazing performance in face detection. That is, the deep learning methods present higher detection accuracy and stronger robustness than the traditional methods like AdaBoost and DPM mentioned above.…”

Section: Introductionmentioning

confidence: 99%

YOLOv3 Attention Face Detector with High Accuracy and Efficiency

Liu¹,

Lü²,

Lan³

2021

Computer Systems Science and Engineering

View full text Add to dashboard Cite

In recent years, face detection has attracted much attention and achieved great progress due to its extensively practical applications in the field of face based computer vision. However, the tradeoff between accuracy and efficiency of the face detectors still needs to be further studied. In this paper, using Darknet-53 as backbone, we propose an improved YOLOv3-attention model by introducing attention mechanism and data augmentation to obtain the robust face detector with high accuracy and efficiency. The attention mechanism is introduced to enhance much higher discrimination of the deep features, and the trick of data augmentation is used in the training procedure to achieve higher detection accuracy without significantly affecting the inference speed. The model has been trained and evaluated on the popular and challenging face detection benchmark, i.e., the WIDER FACE training and validation subsets, respectively, achieving AP of 0.942, 0.919 and 0.821 with the speed of 28FPS. This performance exceeds some existing SOTA algorithms, demonstrating acceptable accuracy and near real time detection for VGA resolution images, even in the complex scenarios. In addition, the proposed model shows good generation ability on another public dataset FDDB. The results indicate the proposed model is a promising face detector with high efficiency and accuracy in the wild.

show abstract

Detecting small faces in the wild based on generative adversarial network and contextual information

Cited by 29 publications

References 51 publications

Detecting faces in specific scenarios: Systematic Literature Review

Detecting faces in specific scenarios: Systematic Literature Review

Mars Image Super-Resolution Based on Generative Adversarial Network

YOLOv3 Attention Face Detector with High Accuracy and Efficiency

Contact Info

Product

Resources

About