2 code implementations • 5 Dec 2023 • Xiaohu Lu, Hayder Radha
Universal adversarial attack methods such as Fast Sign Gradient Method (FSGM) and Projected Gradient Descend (PGD) are popular for LiDAR object detection, but they are often deficient compared to task-specific adversarial attacks.
no code implementations • 12 Sep 2023 • Xiaohu Lu, Hayder Radha
The extension from single-target to multi-target domain adaptation is accomplished by exploring the class-wise distance relationship between domains and replacing the strong representative set with much stronger samples from peer domains via peer scaffolding.
no code implementations • 30 Apr 2023 • Su Pang, Daniel Morris, Hayder Radha
The second module learns radar features from multiple radar scans and then applies transformer decoder to learn the interactions between radar features and vision-updated queries.
no code implementations • 7 Feb 2022 • Mazin Hnewa, Hayder Radha
In this paper, we introduce a novel MultiScale Domain Adaptive YOLO (MS-DAYOLO) framework that employs multiple domain adaptation paths and corresponding domain classifiers at different scales of the recently introduced YOLOv4 object detector.
1 code implementation • 2 Jun 2021 • Mazin Hnewa, Hayder Radha
The area of domain adaptation has been instrumental in addressing the domain shift problem encountered by many applications.
no code implementations • 13 Mar 2021 • Su Pang, Hayder Radha
The ability of an autonomous vehicle to perform 3D tracking is essential for safe planing and navigation in cluttered environments.
1 code implementation • 2 Sep 2020 • Su Pang, Daniel Morris, Hayder Radha
There have been significant advances in neural networks for both 3D object detection using LiDAR and 2D object detection using video.
no code implementations • 30 Jun 2020 • Mazin Hnewa, Hayder Radha
Advanced automotive active-safety systems, in general, and autonomous vehicles, in particular, rely heavily on visual data to classify and localize objects such as pedestrians, traffic signs and lights, and other nearby cars, to assist the corresponding vehicles maneuver safely in their environments.
no code implementations • 17 Nov 2015 • Iman Barjasteh, Rana Forsati, Abdol-Hossein Esfahanian, Hayder Radha
We propose a semi-supervised collaborative ranking model, dubbed \texttt{S$^2$COR}, to improve the quality of cold-start recommendation.
no code implementations • 2 Aug 2015 • Mohammad Aghagolzadeh, Hayder Radha
In particular, we rely on the spatial diversity of compressive measurements to guarantee that the solution is unique with a high probability.
no code implementations • 2 Aug 2015 • Mohammad Aghagolzadeh, Hayder Radha
In this paper, we study the problem of hyperspectral pixel classification based on the recently proposed architectures for compressive whisk-broom hyperspectral imagers without the need to reconstruct the complete data cube.
no code implementations • 13 Oct 2014 • Chinh Dang, Hayder Radha
Third, and to further achieve lower computational complexity, we perform hierarchical clustering on the optimal subset based on Grassmann manifold distances.
no code implementations • 7 May 2014 • Chinh Dang, Hayder Radha
We refer to the proposed representative selection framework as a Sparse Graph and Grassmann Manifold (SGGM) based approach.
no code implementations • 7 May 2014 • Chinh Dang, Abdolreza Moghadam, Hayder Radha
Key frame extraction algorithms consider the problem of selecting a subset of the most informative frames from a video to summarize its content.