HRHayder Radha

Hayder Radha

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hayder Radha has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    TransCAR: Transformer-based Camera-And-Radar Fusion for 3D Object Detection

    by Su Pang, Daniel Morris, Hayder Radha

    Despite radar's popularity in the automotive industry, for fusion-based 3D object detection, most existing works focus on LiDAR and camera fusion. In this paper, we propose TransCAR, a Transformer-based Camera-And-Radar fusion solution for 3D object detection. Our TransCAR consists of two modules. The first module learns 2D features from surround-view camera images and then uses a sparse set of 3D object queries to index into these 2D features. The vision-updated queries then interact with each other via transformer self-attention layer. 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. The cross-attention layer within the transformer decoder can adaptively learn the soft-association between the radar features and vision-updated queries instead of hard-association based on sensor calibration only. Finally, our model estimates a bounding box per query using set-to-set Hungarian loss, which enables the method to avoid non-maximum suppression. TransCAR improves the velocity estimation using the radar scans without temporal information. The superior experimental results of our TransCAR on the challenging nuScenes datasets illustrate that our TransCAR outperforms state-of-the-art Camera-Radar fusion-based 3D object detection approaches.


  • Open Access

    Multiscale Domain Adaptive YOLO for Cross-Domain Object Detection

    by Mazin Hnewa, Hayder Radha

    The area of domain adaptation has been instrumental in addressing the domain shift problem encountered by many applications. This problem arises due to the difference between the distributions of source data used for training in comparison with target data used during realistic testing scenarios. 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 to generate domain-invariant features. We train and test our proposed method using popular datasets. Our experiments show significant improvements in object detection performance when training YOLOv4 using the proposed MS-DAYOLO and when tested on target data representing challenging weather conditions for autonomous driving applications.

  • A Point Target Model for Interferometric Radar Angular Velocity Estimation

    by Eric Klinefelter, Jason Merlo, Hayder Radha, Jeffrey A. Nanzer

    In this work, we derive the exact response of an interferometric correlation radar to an arbitrary scene containing N independent point scatterers. The response of an interferometric radar to multiple targets can be complicated by the nonlinear processing, which generates intermodulation responses in addition to the desired fundamental frequency responses. An accurate signal model is critical for predicting and mitigating these intermodulation products and allows for model-based parameter estimation methods to be used to estimate target angular velocity. We derive a general response to an arbitrary number of independent targets and validate both the exact model and a simpler approximate model via simulation and experimental measurement with a 38-GHz continuous-wave interferometric radar. The experiment contains two targets traveling perpendicular to the radar's line-of-sight on linear stages at speeds of 0.36 and 0.5 m/s. We use an error metric to describe the similarity between the measured or simulated time-frequency response and the time-frequency response of a signal generated using the frequency estimates of either the exact or approximate models and show that in regimes where the small-angle approximation holds, both models provide an accurate representation of the measured or simulated interferometric response, demonstrating the feasibility of these models.


  • Open Access

    Semi-supervised Collaborative Ranking with Push at Top

    by Iman Barjasteh, Rana Forsati, Abdol-Hossein Esfahanian, Hayder Radha

    Existing collaborative ranking based recommender systems tend to perform best when there is enough observed ratings for each user and the observation is made completely at random. Under this setting recommender systems can properly suggest a list of recommendations according to the user interests. However, when the observed ratings are extremely sparse (e.g. in the case of cold-start users where no rating data is available), and are not sampled uniformly at random, existing ranking methods fail to effectively leverage side information to transduct the knowledge from existing ratings to unobserved ones. We propose a semi-supervised collaborative ranking model, dubbed \texttt{S$^2$COR}, to improve the quality of cold-start recommendation. \texttt{S$^2$COR} mitigates the sparsity issue by leveraging side information about both observed and missing ratings by collaboratively learning the ranking model. This enables it to deal with the case of missing data not at random, but to also effectively incorporate the available side information in transduction. We experimentally evaluated our proposed algorithm on a number of challenging real-world datasets and compared against state-of-the-art models for cold-start recommendation. We report significantly higher quality recommendations with our algorithm compared to the state-of-the-art.

  • Open Access

    New Guarantees for Blind Compressed Sensing

    by Mohammad Aghagolzadeh, Hayder Radha

    Blind Compressed Sensing (BCS) is an extension of Compressed Sensing (CS) where the optimal sparsifying dictionary is assumed to be unknown and subject to estimation (in addition to the CS sparse coefficients). Since the emergence of BCS, dictionary learning, a.k.a. sparse coding, has been studied as a matrix factorization problem where its sample complexity, uniqueness and identifiability have been addressed thoroughly. However, in spite of the strong connections between BCS and sparse coding, recent results from the sparse coding problem area have not been exploited within the context of BCS. In particular, prior BCS efforts have focused on learning constrained and complete dictionaries that limit the scope and utility of these efforts. In this paper, we develop new theoretical bounds for perfect recovery for the general unconstrained BCS problem. These unconstrained BCS bounds cover the case of overcomplete dictionaries, and hence, they go well beyond the existing BCS theory. Our perfect recovery results integrate the combinatorial theories of sparse coding with some of the recent results from low-rank matrix recovery. In particular, we propose an efficient CS measurement scheme that results in practical recovery bounds for BCS. Moreover, we discuss the performance of BCS under polynomial-time sparse coding algorithms.

  • Open Access

    Scalable Video Transcaling for the Wireless Internet

    by Hayder Radha, Mihaela van der Schaar, Shirish Karande


  • Adaptive overcomplete wavelet video coding with spatial transcaling

    by Mihaela van der Schaar, Jong Chul Ye, Hayder Radha

    The unprecedented increase in the level of heterogeneity of emerging wireless networks and the mobile Internet emphasizes the need for scalable and adaptive video solutions both for coding and transmission purposes. However, in general, there is an inherent tradeoff between the level of scalability (e.g., in terms of bitrate range, levels of spatial resolutions, and/or levels of temporal resolutions) and the video-coding penalty incurred by such scalable video schemes as compared to non-scalable coders. In other words, the higher the level of scalability, the lower the overall video quality of the scalable stream that is needed to support the desired scalability level. In [1][2][3], we introduced the notion of TranScaling, which is a generalization of (non-scalable) transcoding. With TranScaling, a scalable video stream covering a given bandwidth range, is mapped into one or more scalable video streams covering different bandwidth ranges. In this paper, we illustrate the benefits of Spatial TranScaling in the context of a recently developed scalable and adaptive inband motion compensated temporal filtering scheme (IBMCTF) [4][5]. We show how using TranScaling, the already high coding efficiency performance of such adaptive IBMCTF schemes can be further improved.