S
Shoaib Ahmed Siddiqui
Researcher at German Research Centre for Artificial Intelligence
Publications - 41
Citations - 2162
Shoaib Ahmed Siddiqui is an academic researcher from German Research Centre for Artificial Intelligence. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 10, co-authored 33 publications receiving 1069 citations. Previous affiliations of Shoaib Ahmed Siddiqui include University of the Sciences & Kaiserslautern University of Technology.
Papers
More filters
Proceedings Article
Deep One-Class Classification
Lukas Ruff,Robert A. Vandermeulen,Nico Goernitz,Lucas Deecke,Shoaib Ahmed Siddiqui,Alexander Binder,Emmanuel Müller,Marius Kloft +7 more
TL;DR: This paper introduces a new anomaly detection method—Deep Support Vector Data Description—, which is trained on an anomaly detection based objective and shows the effectiveness of the method on MNIST and CIFAR-10 image benchmark datasets as well as on the detection of adversarial examples of GTSRB stop signs.
Journal ArticleDOI
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
TL;DR: A novel deep learning-based anomaly detection approach (DeepAnT) for time series data, which is equally applicable to the non-streaming cases and outperforms the state-of-the-art anomaly detection methods in most of the cases, while performing on par with others.
Journal ArticleDOI
Automatic fish species classification in underwater videos: exploiting pre-trained deep neural network models to compensate for limited labelled data
Shoaib Ahmed Siddiqui,Ahmad Salman,Muhammad Imran Malik,Faisal Shafait,Ajmal Mian,Mark R. Shortis,Euan S. Harvey +6 more
TL;DR: This research advocates that the development of automated classification systems which can identify fish from underwater video imagery is feasible and a cost-effective alternative to manual identification by humans.
Journal ArticleDOI
Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning
Muhammad Naseer Bajwa,Muhammad Naseer Bajwa,Muhammad Imran Malik,Shoaib Ahmed Siddiqui,Shoaib Ahmed Siddiqui,Andreas Dengel,Andreas Dengel,Faisal Shafait,Wolfgang Neumeier,Sheraz Ahmed +9 more
TL;DR: A two-stage framework that first detects and localizes optic disc and then classifies it into healthy or glaucomatous and a rule-based semi-automatic ground truth generation method that provides necessary annotations for training RCNN based model for automated disc localization is developed.
Journal ArticleDOI
DeCNT: Deep Deformable CNN for Table Detection
TL;DR: The presented approach was able to surpass the state-of-the-art performance on both ICDAR-2013 and ICDar-2017 POD datasets with a F-measure of 0.994 and 0.968, respectively, indicating its effectiveness and superiority for the task of table detection.