S
Salman H. Khan
Researcher at University of Engineering and Technology, Lahore
Publications - 74
Citations - 2277
Salman H. Khan is an academic researcher from University of Engineering and Technology, Lahore. The author has contributed to research in topics: Convolutional neural network & Discriminative model. The author has an hindex of 19, co-authored 74 publications receiving 1112 citations. Previous affiliations of Salman H. Khan include Ghulam Ishaq Khan Institute of Engineering Sciences and Technology & Australian National University.
Papers
More filters
Proceedings ArticleDOI
CycleISP: Real Image Restoration via Improved Data Synthesis
Syed Waqas Zamir,Aditya Arora,Salman H. Khan,Munawar Hayat,Fahad Shahbaz Khan,Ming-Hsuan Yang,Ling Shao +6 more
TL;DR: CycleISP as discussed by the authors is a framework that models camera imaging pipeline in forward and reverse directions, which allows to produce any number of realistic image pairs for denoising both in RAW and sRGB spaces.
Proceedings ArticleDOI
A Self-supervised Approach for Adversarial Robustness
TL;DR: This paper proposes a self-supervised adversarial training mechanism in the input space that provides significant robustness against the unseen adversarial attacks and can be deployed as a plug-and-play solution to protect a variety of vision systems, as it demonstrates for the case of classification, segmentation and detection.
Posted Content
Transformers in Vision: A Survey
Salman H. Khan,Muzammal Naseer,Munawar Hayat,Syed Waqas Zamir,Fahad Shahbaz Khan,Mubarak Shah +5 more
TL;DR: Transformer networks as mentioned in this paper enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM).
Posted Content
CycleISP: Real Image Restoration via Improved Data Synthesis
Syed Waqas Zamir,Aditya Arora,Salman H. Khan,Munawar Hayat,Fahad Shahbaz Khan,Ming-Hsuan Yang,Ling Shao +6 more
TL;DR: This paper presents a framework that models camera imaging pipeline in forward and reverse directions that allows any number of realistic image pairs for denoising both in RAW and sRGB spaces and achieves the state-of-the-art performance on real camera benchmark datasets.
Proceedings Article
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
Syed Waqas Zamir,Aditya Arora,Akshita Gupta,Salman H. Khan,Guolei Sun,Fahad Shahbaz Khan,Fan Zhu,Ling Shao,Gui-Song Xia,Xiang Bai +9 more
TL;DR: This work introduces the first benchmark dataset for instance segmentation in aerial imagery that combines instance-level object detection and pixel-level segmentation tasks, and introduces a large-scale and densely annotated Instance Segmentation in Aerial Images Dataset (iSAID).