MMMichael G. Madden

Michael G. Madden

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Michael G. Madden has a total of 130 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • BHCP-DOC: A Real-World Bilingual Dataset for Handwritten Clinical Prescription Detection and Recognition

    by Fatima Bukhari, Mickael Coustaty, Muhammad Muzzamil Luqman, Souhail Bakkali, Michael G. Madden, Nadeem Iqbal Kajla

  • Open Access

    Predictors and characterization of non-calcified plaques among patients with a zero coronary calcium score

    by Sara Alsubai, Foziyah Alqahtani, Sara Sgreva, Emiliano Bianchini, Aduba Chukwunwike, Ruth Sharif, Hesham Elzomor, Naeif Almagal, Shahad Almotairi, Muhammad Yusha Malik, et al.

  • Open Access

    Contextual Graph Modeling for Open-Set Object Detection in Multi-View Autonomous Driving

    by Muhammad Asad, Ihsan Ullah, Ganesh Sistu, Michael G. Madden

    Autonomous vehicles require robust perception systems capable of accurately identifying both known and unknown objects in complex driving environments. Traditional closed-set detectors risk safety by failing to recognize novel or out-of-distribution (OOD) objects. This work introduces a contextual graph-based framework for open-set object detection in multi-view autonomous driving. We also introduce a novel dataset, NuScenes-Novel, which is enhanced with additional and unusual objects from the MS-COCO dataset to form a more realistic benchmark. Detected objects are represented as nodes in graphs, where spatial and contextual relationships are established through distance metrics. Each object's appearance and geometric features are embedded using a DINOv2 backbone, and a Variational Graph Auto-Encoder (VGAE) is trained to learn the contextual structure and relationships within each scene. During inference, VGAE reconstruction errors are fused with a context-aware Mahalanobis distance to identify OOD objects effectively. On NuScenes-Novel (aggregated over six cameras), the proposed fusion achieves an AUROC of 0.98 and an FPR@95 of 0.07, which shows strong separation between in-distribution and novel objects across multi-view scenes. Integrating appearance and relational context improves robustness under occlusion and varying objects. The results demonstrate that modeling object relationships and leveraging graph-based reasoning significantly improve the reliability and robustness of perception in autonomous vehicles. These findings show the importance of considering contextual information and a hybrid scoring approach for open-set detection.

  • Open Access

    Rig-Robust BEV Perception via 3D Gaussian Splatting and Cyclic Self-Supervision

    by Muhammad Adeel Hafeez, Ganesh Sistu, Venkatesh Moorthi, Michael G. Madden, Ihsan Ullah

    Camera rigs for Advanced Driver Assistance Systems (ADAS) are subject to design choices of each vehicle variant; therefore, ADAS algorithms should be rig-invariant or tunable with limited additional data. Recently, the ADAS community adopted BEV (Bird’s Eye View) perception and planning systems due to their scalability to heterogeneous sensors, computational efficiency, and ego-centric perception, but BEV methods remain highly rig-dependent. To verify this, we study a camera-only BEV model, GaussianLSS, which lifts images into a 3D Gaussian scene and predicts BEV maps. We observe a sharp performance drop under a Sedan-to-SUV rig change, with a similar degradation in the reverse direction. Overlap between predicted and ground-truth BEV maps, measured by intersection-over-union (IoU), falls from 38.42% to 18.30% when trained on Sedan and tested on SUV. To address this, we propose a training-time extension to GaussianLSS that improves cross-rig robustness without using any target-rig images or BEV labels. Starting from sedan images, GaussianLSS lifts features into a 3D Gaussian scene, which we render into rig-aware perspective features for both Sedan and SUV. A lightweight decoder is trained only on sedan perspective features to reconstruct sedan RGB (re-projecting features back to the input image) and is then frozen. During cyclic fine-tuning, SUV perspective features rendered from the same Gaussians are passed through the frozen decoder to produce pseudo-SUV views that provide self-supervision for the BEV model in world/BEV space. This increases SUV performance to 23.46% IoU while keeping Sedan performance near its upper bound, and to 25.15% when the decoder additionally sees 20% SUV RGB (the BEV model still uses no SUV labels). The decoder is not used at inference, keeping deployment cost unchanged while suggests a path toward reducing the need for per-vehicle data collection and annotation.

  • PoisonShield-FL-NIDS: A Robust Defense Against Poisoning Attacks in Federated Learning Intrusion Detection

    by Muhammad Ilyas, Nadeem Iqbal Kajla, Michael G. Madden, Gaojuan Fan, Chongsheng Zhang, Hafiz Muhammad Sanaullah Badar

    Federated learning (FL) has emerged as a privacy-preserving paradigm for collaborative intrusion detection in networked environments. However, it remains vulnerable to poisoning attacks (PAs) wherein malicious clients can corrupt the global model through deceptive updates. To address this, we propose PoisonShield-FL-network intrusion detection systems (NIDS), a robust FL-based intrusion detection system that integrates client-side anomaly filtering with trust-aware aggregation to defend against poisoned contributions. Experimental evaluation under varying levels of adversarial influence demonstrates that PoisonShield-FL-NIDS achieves superior performance across key metrics, attaining 93% accuracy, 91% precision, 94% recall, and an AUC of 0.96, while maintaining a low robustness index $ \text {RI}~\lt 0.05 $ even with 30% compromised clients. Compared to baseline FL models such as FL-CNN and FedACNN, our framework demonstrates faster convergence and higher resilience with only a marginal increase in communication overhead.


  • Open Access

    Multi-Source Depth Estimation: Utilizing Real, Synthetic, and Monocular Depth Data with Custom Loss Functions

    by Muhammad Adeel Hafeez, Ganesh Sistu, Michael G. Madden, Ihsan Ullah

    Depth estimation from 2D images is an essential task in computer vision with applications in scene understanding, robotics, and autonomous systems. The performance of supervised depth models depends on network design, loss formulation, data quality, and fine-tuning strategy. In this study, we propose a progressive fine-tuning approach for metric (absolute-scale) depth estimation. Our method uses transfer learning across multiple indoor datasets: real, synthetic, and pseudo-labelled. DenseNet-169 and EfficientNet-B0 backbones are fine-tuned on MIT-G, SUN-RGBD, SceneNet, and NYU2. We apply a three-scale combined loss with weighted MAE + Edge + SSIM terms at full, 1/2, and 1/4 resolution, and add a perceptual VGG component, while we keep the global coefficients of the loss at 1 for simplicity and reproducibility. We find that EfficientNet performs better on the smaller datasets, while DenseNet benefits most from the million-image SceneNet stage and reaches REL 0.105 and RMSE 0.359 on NYU2, comparable to recent transformer baselines yet using 6 $$\times $$ × fewer parameters. The pseudo-labelled MIT-G data is used as a warm-start and shows the potential of reducing annotation cost. All headline metrics results are based on sensor ground-truth data, avoiding circular evaluation. Qualitative analysis and zero-shot tests on the unseen iBims-1 benchmark confirm that the models generalise and produce coherent, detailed depth maps across diverse indoor scenes. The proposed pipeline thus offers a balanced trade-off between accuracy and computational cost for practical indoor depth estimation.


  • Open Access

    Towards Robust Autonomous Driving: Out-of-Distribution Object Detection in Bird's Eye View Space

    by Muhammad Asad, Ihsan Ullah, Ganesh Sistu, Michael G. Madden

    In autonomous driving, understanding the surroundings is crucial for safety. Since most object detection systems are designed to identify known objects, they may miss unknown or novel objects, which can be dangerous. This study addresses Out-Of-Distribution (OOD) detection for vehicle-like unknown objects within the Bird's Eye View (BeV) space, a top-down representation of the environment that provides a comprehensive spatial layout crucial for scene understanding. Enhancing the model's adaptability to unfamiliar objects, we present two novel methods for detecting unknown objects in BeV space. Specifically, we introduce random patches and OOD objects in the environment to help the model identify both known objects, such as vehicles, and OOD objects. We also introduce a new dataset, NuScenesOOD, derived from the NuScenes dataset, which augments vehicles with patterns and shapes to challenge the model. Additionally, we address challenges such as patch size inconsistency and occlusion from moving frames in BeV space. Our method targets vehicle-shaped anomalies in the planar driving space, maintaining high accuracy for known and enhancing detection of unknown objects. This research contributes to making future autonomous vehicles safer by improving their ability to detect diverse vehicle like OOD objects in their environment. Code is available at: https://github.com/asad-python/OOD-in-BEV


  • Open Access

    A Probabilistic Adversarial Autoencoder for Novelty Detection: Leveraging Lightweight Design and Reconstruction Loss

    by Muhammad Asad, Ihsan Ullah, Muhammad Adeel Hafeez, Ganesh Sistu, Michael G. Madden

    A novelty detection task involves identifying whether a data point is an outlier, given a training dataset that primarily captures the distribution of inliers. The novel class is usually absent, poorly sampled, or not well defined in the training data. A common technique for anomaly detection at present is to use an adversarial network generator to generate an anomaly score for inputs using the reconstruction loss. However, because this technique uses a competitive training process, it can be unreliable, with its performance being inconsistent during each adversarial training step. This inconsistency arises from changes in the network’s ability to detect anomalies. In this paper, we propose a revised framework for generative probabilistic novelty detection. We use a similar adversarial autoencoder-based framework but with a lightweight deep network, a novel training paradigm, and a probabilistic score to compute the reconstruction loss. Our methodology calculates the probability of whether a sample comes from the inlier distribution or not. The proposed approach can be applied to anomaly and outlier detection in images and videos. We present the results on multiple benchmark datasets, including the challenging UCSD Ped2 dataset for video anomaly detection. Our results illustrate that our proposed method learns the inlier classes and differentiates them from the outlier classes effectively, leading to better results than the baseline and state-of-the-art methods in several benchmark datasets.