Automated Testing of Graphics Units by Deep-Learning Detection of Visual Anomalies

被引：0

作者：

Faivishevsky, Lev ^{[1
]}

Szeskin, Adi ^{[1
]}

Muppalla, Ashwin K. ^{[1
]}

Shwartz-Ziv, Ravid ^{[1
]}

Ben Ari, Itamar ^{[1
]}

Laperdon, Ronen ^{[1
]}

Melloul, Benjamin ^{[1
]}

Hollander, Tahi ^{[1
]}

Hope, Tom ^{[1
]}

Armon, Amitai ^{[1
]}

机构：

[1] Intel, It Artificial Intelligence & Visual Proc Grp, Santa Clara, CA 95054 USA

来源：

KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING | 2021年

关键词：

deep learning; graphics processors validation; computer vision; anomaly detection; multiple instance learning;

D O I：

10.1145/3447548.3467116

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a novel system for performing real-time detection of diverse visual corruptions in videos, for validating the quality of graphics units in our company. The system is used for several types of content, including movies and 3D graphics, with strict constraints on low false alert rates and real-time processing of millions of video frames per day. These constraints required novel solutions involving both hardware and software, including new supervised and weakly-supervised methods we developed. Our deployed system has enabled a 20X reduction of human effort and discovering new corruptions missed by humans and existing approaches.

引用

页码：2811 / 2821

页数：11

共 30 条

[1]

Avidan Eran, 2018, REAL TIME DEEP LEARN

[2]

Berthelot D., 2017, arXiv, DOI DOI 10.48550/ARXIV.1703.10717

[3]

Bholowalia P., 2014, International Journal of Computer Applications, V105, DOI DOI 10.5120/18405-9674

[4]

Brock Andrew, 2018, P 7 ACM INT S PERV D, DOI DOI 10.1145/3205873.3205877

[5]

Calinski T., 1974, Communications in Statistics-theory and Methods, V3, P1, DOI [DOI 10.1080/03610927408827101, 10.1080/03610927408827101]

[6] Estimates of the information content and dimensionality of natural scenes from proximity distributions [J].

Chandler, Damon M. ;

Field, David J. .

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2007, 24 (04) :922-941

[7] Learning Spatiotemporal Features with 3D Convolutional Networks [J].

Du Tran ;

Bourdev, Lubomir ;

Fergus, Rob ;

Torresani, Lorenzo ;

Paluri, Manohar .

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :4489-4497

[8]

Ester M., 1996, P 2 INT C KNOWL DISC, P226, DOI DOI 10.5555/3001460.3001507

[9]

Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672

[10]

He K., 2015, C COMPUTER VISION PA, DOI DOI 10.1109/CVPR.2016.90

← 1 2 3 →