Hayder Radha

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.

Hamed Khatounabadi, Xiaohu Lu, Hayder Radha

The performance of state-of-the-art object detectors degrades significantly under adverse weather, causing a safety-critical domain shift problem for autonomous vehicles. Recent efforts address this problem by relying on synthetic data to train the object detectors, which limits their real-world applicability. Meanwhile, pseudo-labeling is widely used for cross-dataset domain adaptation problems. However, these methods have not been exploited by weather-based domain adaptation approaches due to the noisy nature of such labels generated under harsh weather conditions. In this paper, we propose two new approaches to mitigate this weather-induced domain shift. First, we propose a Weather-Induced pseudo Label Denoising (WILD) framework that filters noisy pseudo labels generated by real data captured under adverse weather conditions. Second, we develop a novel hybrid training methodology, WILD SAM, that exploits both pseudo-label denoising and simulation-based training solutions while using real-data from the target harsh-weather domain. We validate both proposed approaches, WILD and WILD SAM, on the recently released Four Seasons dataset across rainy and snowy scenarios. Experiments show that the proposed frameworks improve Average Precision (AP) up to 13\% and significantly reduce the weather-induced performance gap relative to the baseline. The code is available at: https://github.com/Kh-Hamed/WILD-SAM

Xiaohu Lu, Hayder Radha

Unsupervised domain adaptation (UDA) focuses on transferring knowledge learned in the labeled source domain to the unlabeled target domain. Despite significant progress that has been achieved in single-target domain adaptation for image classification in recent years, the extension from single-target to multi-target domain adaptation is still a largely unexplored problem area. In general, unsupervised domain adaptation faces a major challenge when attempting to learn reliable information from a single unlabeled target domain. Increasing the number of unlabeled target domains further exacerbate the problem rather significantly. In this paper, we propose a novel strong-weak integrated semi-supervision (SWISS) learning strategy for image classification using unsupervised domain adaptation that works well for both single-target and multi-target scenarios. Under the proposed SWISS-UDA framework, a strong representative set with high confidence but low diversity target domain samples and a weak representative set with low confidence but high diversity target domain samples are updated constantly during the training process. Both sets are fused to generate an augmented strong-weak training batch with pseudo-labels to train the network during every iteration. 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. Moreover, a novel adversarial logit loss is proposed to reduce the intra-class divergence between source and target domains, which is back-propagated adversarially with a gradient reverse layer between the classifier and the rest of the network. Experimental results based on three benchmarks, Office-31, Office-Home, and DomainNet, show the effectiveness of the proposed SWISS framework.

Ce Zhou, Qiben Yan, Daniel Kent et al.

Monocular Depth Estimation (MDE) plays a crucial role in vision-based Autonomous Driving (AD) systems. It utilizes a single-camera image to determine the depth of objects, facilitating driving decisions such as braking a few meters in front of a detected obstacle or changing lanes to avoid collision. In this paper, we investigate the security risks associated with monocular vision-based depth estimation algorithms utilized by AD systems. By exploiting the vulnerabilities of MDE and the principles of optical lenses, we introduce LensAttack, a physical attack that involves strategically placing optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths. LensAttack encompasses two attack formats: concave lens attack and convex lens attack, each utilizing different optical lenses to induce false depth perception. We begin by constructing a mathematical model of our attack, incorporating various attack parameters. Subsequently, we simulate the attack and evaluate its real-world performance in driving scenarios to demonstrate its effect on state-of-the-art MDE models. The results highlight the significant impact of LensAttack on the accuracy of depth estimation in AD systems.

Xiaohu Lu, Hayder Radha

The adversarial robustness of a model is its ability to resist adversarial attacks in the form of small perturbations to input data. 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. Additionally, these universal methods typically require unrestricted access to the model's information, which is difficult to obtain in real-world applications. To address these limitations, we present a black-box Scaling Adversarial Robustness (ScAR) method for LiDAR object detection. By analyzing the statistical characteristics of 3D object detection datasets such as KITTI, Waymo, and nuScenes, we have found that the model's prediction is sensitive to scaling of 3D instances. We propose three black-box scaling adversarial attack methods based on the available information: model-aware attack, distribution-aware attack, and blind attack. We also introduce a strategy for generating scaling adversarial examples to improve the model's robustness against these three scaling adversarial attacks. Comparison with other methods on public datasets under different 3D object detection architectures demonstrates the effectiveness of our proposed method. Our code is available at https://github.com/xiaohulugo/ScAR-IROS2023.

Aryan Gondkar, Hayder Radha, Yiming Deng

Detecting out-of-distribution (OOD) samples is critical for safe deployment of neural networks in safety-critical applications. While maximum softmax probability (MSP) provides a simple baseline, it lacks theoretical grounding and suffers from miscalibration. We propose VNDUQE (VIB-based Novelty Detection and Uncertainty Quantification for Nondestructive Evaluation), which investigates novelty detection through the Deep Variational Information Bottleneck (VIB), which explicitly constrains information flow through learned representations. We train VIB models on MNIST with held-out digit classes and evaluate OOD detection using information-theoretic metrics: KL divergence and prediction entropy. Our results reveal complementary detection signals: KL divergence achieves perfect detection (100\% AUROC on noise) on far-OOD samples (noise, domain shift), while prediction entropy excels at near-OOD detection (94.7\% AUROC on novel digit classes). A parallel detection strategy combining both metrics achieves 95.3\% average AUROC and 92\% true positive rate at 5\% false positive rate, which is a 32 percentage point improvement over baseline MSP (85.0\% AUROC, 60.1\% TPR). Compression via the information bottleneck principle ($β=10^{-3}$) reduces Expected Calibration Error by 38\%, demonstrating that information-theoretic constraints produce fundamentally more reliable uncertainty estimates. These findings directly support active learning with expensive computational oracles, where well-calibrated novelty detection enables principled threshold selection for oracle queries.

Xiaohu Lu, Hayder Radha

Object detection using LiDAR point clouds relies on a large amount of human-annotated samples when training the underlying detectors' deep neural networks. However, generating 3D bounding box annotation for a large-scale dataset could be costly and time-consuming. Alternatively, unsupervised domain adaptation (UDA) enables a given object detector to operate on a novel new data, with unlabeled training dataset, by transferring the knowledge learned from training labeled \textit{source domain} data to the new unlabeled \textit{target domain}. Pseudo label strategies, which involve training the 3D object detector using target-domain predicted bounding boxes from a pre-trained model, are commonly used in UDA. However, these pseudo labels often introduce noise, impacting performance. In this paper, we introduce the Domain Adaptive LIdar (DALI) object detection framework to address noise at both distribution and instance levels. Firstly, a post-training size normalization (PTSN) strategy is developed to mitigate bias in pseudo label size distribution by identifying an unbiased scale after network training. To address instance-level noise between pseudo labels and corresponding point clouds, two pseudo point clouds generation (PPCG) strategies, ray-constrained and constraint-free, are developed to generate pseudo point clouds for each instance, ensuring the consistency between pseudo labels and pseudo points during training. We demonstrate the effectiveness of our method on the publicly available and popular datasets KITTI, Waymo, and nuScenes. We show that the proposed DALI framework achieves state-of-the-art results and outperforms leading approaches on most of the domain adaptation tasks. Our code is available at \href{https://github.com/xiaohulugo/T-RO2024-DALI}{https://github.com/xiaohulugo/T-RO2024-DALI}.

Xiaohu Lu, Hamed Khatounabadi, Hayder Radha

With the advancement of autonomous driving, numerous annotated multi-modality datasets have become available. This presents an opportunity to develop domain-adaptive 3D object detectors for new environments without relying on labor-intensive manual annotations. However, traditional domain adaptation methods typically focus on a single source domain or a single modality, limiting their effectiveness in multi-source, multi-modality scenarios. In this paper, we propose a novel framework for multi-source, multi-modality unsupervised domain adaptation in 3D object detection for autonomous driving. Given multiple labeled source domains and one unlabeled target domain, our framework first introduces hierarchical spatially-conditioned (HSC) domain classifiers, which jointly align features from both camera and LiDAR modalities at two distinct levels for each source-target domain pair. To effectively leverage information from multiple source domains, we construct a prototype graph between each pair of domains. Based on this, we develop a prototype graph weighted (PGW) multi-source fusion strategy to aggregate predictions from multiple source detection heads. Experimental results on three widely used 3D object detection datasets - Waymo, nuScenes, and Lyft - demonstrate that our proposed framework effectively integrates information across both modalities and source domains, consistently outperforming state-of-the-art methods.

Armin Maleki, Hayder Radha

Collaborative perception (CP) is a promising paradigm for improving situational awareness in autonomous vehicles by overcoming the limitations of single-agent perception. However, most existing approaches assume homogeneous agents, which restricts their applicability in real-world scenarios where vehicles use diverse sensors and perception models. This heterogeneity introduces a feature domain gap that degrades detection performance. Prior works address this issue by retraining entire models/major components, or using feature interpreters for each new agent type, which is computationally expensive, compromises privacy, and may reduce single-agent accuracy. We propose Faster-HEAL, a lightweight and privacy-preserving CP framework that fine-tunes a low-rank visual prompt to align heterogeneous features with a unified feature space while leveraging pyramid fusion for robust feature aggregation. This approach reduces the trainable parameters by 94%, enabling efficient adaptation to new agents without retraining large models. Experiments on the OPV2V-H dataset show that Faster-HEAL improves detection performance by 2% over state-of-the-art methods with significantly lower computational overhead, offering a practical solution for scalable heterogeneous CP.

Ce Zhou, Qiben Yan, Daniel Kent et al.

Monocular Depth Estimation (MDE) is a pivotal component of vision-based Autonomous Driving (AD) systems, enabling vehicles to estimate the depth of surrounding objects using a single camera image. This estimation guides essential driving decisions, such as braking before an obstacle or changing lanes to avoid collisions. In this paper, we explore vulnerabilities of MDE algorithms in AD systems, presenting LensAttack, a novel physical attack that strategically places optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths. LensAttack encompasses two attack formats: concave lens attack and convex lens attack, each utilizing different optical lenses to induce false depth perception. We first develop a mathematical model that outlines the parameters of the attack, followed by simulations and real-world evaluations to assess its efficacy on state-of-the-art MDE models. Additionally, we adopt an attack optimization method to further enhance the attack success rate by optimizing the attack focal length. To better evaluate the implications of LensAttack on AD, we conduct comprehensive end-to-end system simulations using the CARLA platform. The results reveal that LensAttack can significantly disrupt the depth estimation processes in AD systems, posing a serious threat to their reliability and safety. Finally, we discuss some potential defense methods to mitigate the effects of the proposed attack.

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. Building on our baseline multiscale DAYOLO framework, we introduce three novel deep learning architectures for a Domain Adaptation Network (DAN) that generates domain-invariant features. In particular, we propose a Progressive Feature Reduction (PFR), a Unified Classifier (UC), and an Integrated architecture. We train and test our proposed DAN architectures in conjunction with YOLOv4 using popular datasets. Our experiments show significant improvements in object detection performance when training YOLOv4 using the proposed MS-DAYOLO architectures and when tested on target data for autonomous driving applications. Moreover, MS-DAYOLO framework achieves an order of magnitude real-time speed improvement relative to Faster R-CNN solutions while providing comparable object detection performance.

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.

Su Pang, Hayder Radha

The ability of an autonomous vehicle to perform 3D tracking is essential for safe planing and navigation in cluttered environments. The main challenges for multi-object tracking (MOT) in autonomous driving applications reside in the inherent uncertainties regarding the number of objects, when and where the objects may appear and disappear, and uncertainties regarding objects' states. Random finite set (RFS) based approaches can naturally model these uncertainties accurately and elegantly, and they have been widely used in radar-based tracking applications. In this work, we developed an RFS-based MOT framework for 3D LiDAR data. In partiuclar, we propose a Poisson multi-Bernoulli mixture (PMBM) filter to solve the amodal MOT problem for autonomous driving applications. To the best of our knowledge, this represents a first attempt for employing an RFS-based approach in conjunction with 3D LiDAR data for MOT applications with comprehensive validation using challenging datasets made available by industry leaders. The superior experimental results of our PMBM tracker on public Waymo and Argoverse datasets clearly illustrate that an RFS-based tracker outperforms many state-of-the-art deep learning-based and Kalman filter-based methods, and consequently, these results indicate a great potential for further exploration of RFS-based frameworks for 3D MOT applications.

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. However, it has been surprisingly difficult to train networks to effectively use both modalities in a way that demonstrates gain over single-modality networks. In this paper, we propose a novel Camera-LiDAR Object Candidates (CLOCs) fusion network. CLOCs fusion provides a low-complexity multi-modal fusion framework that significantly improves the performance of single-modality detectors. CLOCs operates on the combined output candidates before Non-Maximum Suppression (NMS) of any 2D and any 3D detector, and is trained to leverage their geometric and semantic consistencies to produce more accurate final 3D and 2D detection results. Our experimental evaluation on the challenging KITTI object detection benchmark, including 3D and bird's eye view metrics, shows significant improvements, especially at long distance, over the state-of-the-art fusion based methods. At time of submission, CLOCs ranks the highest among all the fusion-based methods in the official KITTI leaderboard. We will release our code upon acceptance.

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. However, the performance of object detection methods could degrade rather significantly under challenging weather scenarios including rainy conditions. Despite major advancements in the development of deraining approaches, the impact of rain on object detection has largely been understudied, especially in the context of autonomous driving. The main objective of this paper is to present a tutorial on state-of-the-art and emerging techniques that represent leading candidates for mitigating the influence of rainy conditions on an autonomous vehicle's ability to detect objects. Our goal includes surveying and analyzing the performance of object detection methods trained and tested using visual data captured under clear and rainy conditions. Moreover, we survey and evaluate the efficacy and limitations of leading deraining approaches, deep-learning based domain adaptation, and image translation frameworks that are being considered for addressing the problem of object detection under rainy conditions. Experimental results of a variety of the surveyed techniques are presented as part of this tutorial.

Iman Barjasteh, Rana Forsati, Abdol-Hossein Esfahanian et al.

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.

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. A clear advantage of classification in the compressed domain is its suitability for real-time on-site processing of the sensed data. Moreover, it is assumed that the training process also takes place in the compressed domain, thus, isolating the classification unit from the recovery unit at the receiver's side. We show that, perhaps surprisingly, using distinct measurement matrices for different pixels results in more accuracy of the learned classifier and consistent classification performance, supporting the role of information diversity in learning.

Mohammad Aghagolzadeh, Hayder Radha

This paper tackles algorithmic and theoretical aspects of dictionary learning from incomplete and random block-wise image measurements and the performance of the adaptive dictionary for sparse image recovery. This problem is related to blind compressed sensing in which the sparsifying dictionary or basis is viewed as an unknown variable and subject to estimation during sparse recovery. However, unlike existing guarantees for a successful blind compressed sensing, our results do not rely on additional structural constraints on the learned dictionary or the measured signal. In particular, we rely on the spatial diversity of compressive measurements to guarantee that the solution is unique with a high probability. Moreover, our distinguishing goal is to measure and reduce the estimation error with respect to the ideal dictionary that is based on the complete image. Using recent results from random matrix theory, we show that applying a slightly modified dictionary learning algorithm over compressive measurements results in accurate estimation of the ideal dictionary for large-scale images. Empirically, we experiment with both space-invariant and space-varying sensing matrices and demonstrate the critical role of spatial diversity in measurements. Simulation results confirm that the presented algorithm outperforms the typical non-adaptive sparse recovery based on offline-learned universal dictionaries.

Chinh Dang, Hayder Radha

Image super-resolution remains an important research topic to overcome the limitations of physical acquisition systems, and to support the development of high resolution displays. Previous example-based super-resolution approaches mainly focus on analyzing the co-occurrence properties of low resolution and high-resolution patches. Recently, we proposed a novel single image super-resolution approach based on linear manifold approximation of the high-resolution image-patch space [1]. The image super-resolution problem is then formulated as an optimization problem of searching for the best matched high resolution patch in the manifold for a given low-resolution patch. We developed a novel technique based on the l1 norm sparse graph to learn a set of low dimensional affine spaces or tangent subspaces of the high-resolution patch manifold. The optimization problem is then solved based on the learned set of tangent subspaces. In this paper, we build on our recent work as follows. First, we consider and analyze each tangent subspace as one point in a Grassmann manifold, which helps to compute geodesic pairwise distances among these tangent subspaces. Second, we develop a min-max algorithm to select an optimal subset of tangent subspaces. This optimal subset reduces the computational cost while still preserving the quality of the reconstructed high-resolution image. Third, and to further achieve lower computational complexity, we perform hierarchical clustering on the optimal subset based on Grassmann manifold distances. Finally, we analytically prove the validity of the proposed Grassmann-distance based clustering. A comparison of the obtained results with other state-of-the-art methods clearly indicates the viability of the new proposed framework.

Chinh Dang, Hayder Radha

This paper addresses the problem of identifying a very small subset of data points that belong to a significantly larger massive dataset (i.e., Big Data). The small number of selected data points must adequately represent and faithfully characterize the massive Big Data. Such identification process is known as representative selection [19]. We propose a novel representative selection framework by generating an l1 norm sparse graph for a given Big-Data dataset. The Big Data is partitioned recursively into clusters using a spectral clustering algorithm on the generated sparse graph. We consider each cluster as one point in a Grassmann manifold, and measure the geodesic distance among these points. The distances are further analyzed using a min-max algorithm [1] to extract an optimal subset of clusters. Finally, by considering a sparse subgraph of each selected cluster, we detect a representative using principal component centrality [11]. We refer to the proposed representative selection framework as a Sparse Graph and Grassmann Manifold (SGGM) based approach. To validate the proposed SGGM framework, we apply it onto the problem of video summarization where only few video frames, known as key frames, are selected among a much longer video sequence. A comparison of the results obtained by the proposed algorithm with the ground truth, which is agreed by multiple human judges, and with some state-of-the-art methods clearly indicates the viability of the SGGM framework.

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.