Searcharxiv⌕ Search

arXiv subjects

Masoud Daneshtalab

Publications and source records attributed to Masoud Daneshtalab.

At least 19 recordsLinked to original sources
arXiv2026

FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clients

Federated learning (FL) must serve devices with varying computational capabilities. A fixed model cannot suit all devices, while training one model per deployment limit is costly. Federated supernet training instead learns one elastic model with differently sized subnetworks, then deploys a suitable one to each device. When client inference budgets differ, however, parameters exclusive to high-cost subnetworks are reachable by fewer clients. We propose FEAST, a federated shared-space training framework that counters this imbalance by jointly training multiple subnetworks within each client's limit. Budget-tailored sub-supernet routing sends only the relevant supernet portion, and sparse aggregation merges the returned parameter slices. The trained supernet directly serves the subnetworks used during federation and supports post-hoc extraction of additional subnetworks without federated retraining. We further show that independently assigning clients' training-data volumes and inference budgets can distort accuracy--inference-cost comparisons in heterogeneous FL simulations, and introduce a one-parameter $γ$-allocation protocol to control this coupling. In our experimental setup, the SuperFedNAS and DeepFedNAS supernet training procedures remain near chance at 25M and reach at most $17.09\%$ at $596$M inference MACs; FEAST reaches $71.06\%$ at $596$M, $2.4$ points above the strongest model-heterogeneous weight-sharing baseline at its largest tier. Across CIFAR-100, CINIC-10, and TinyImageNet-200, FEAST achieves the highest population-averaged accuracy among the evaluated weight-sharing methods when each client receives its largest affordable subnetwork. Sub-supernet routing reduces aggregate model-parameter traffic by $6.8\times$ relative to full-supernet transmission.

cs.LG↗
arXiv2026

Reducing the Complexity of Deep Learning Models for EEG Analysis on Wearable Devices

Wearable healthcare devices are the fastest-growing Internet of Things (IoT) sector. Many automated healthcare services rely on two crucial biological signals, namely ECG and EEG, which reflect the activity of the heart and brain, respectively. Although deep neural networks are considered the primary way to process and analyze these signals, the very tight energy and computational power constraints in wearable devices are far below the computational, energy, and memory bandwidth demands of DNN models, thereby impeding the deployment of deep learning in many practical wearable services. This paper investigates the feasibility of deploying state-of-the-art DNN models in resource-constrained wearable devices. Notably, we explore the trade-off between accuracy and computational complexity of DNNs when parameter quantization and electrode reduction methods are used. Our investigation centers on several state-of-the-art DNN models designed for EEG signal analysis, specifically for detecting epileptic seizures. Our findings demonstrate that, when applied judiciously, these techniques can significantly reduce the complexity of the DNNs under consideration with minimal adverse effects on accuracy. These results reveal the explicit trade-offs between accuracy and complexity reduction encountered when adapting DNN-based online EEG analysis for wearable devices.

cs.AI↗
arXiv2026

DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training

Deploying federated learning across heterogeneous IoT device fleets requires tailored neural network architectures for each device class, yet existing Federated Neural Architecture Search (FedNAS) methods suffer from unguided supernet training and prohibitively costly post-training search pipelines that demand over 20 GPU-hours per deployment target. We introduce DeepFedNAS, a two-phase framework built on a multi-objective fitness function that synthesizes information-theoretic network metrics with architectural heuristics. In the first phase, Federated Pareto Optimal Supernet Training replaces random subnet sampling with a pre-computed cache of elite, high-fitness architectures, yielding a superior supernet. In the second phase, a Predictor-Free Search uses this fitness function as a zero-cost accuracy proxy, discovering hardware-optimized subnets in ~20 seconds, a ~61x speedup over the baseline pipeline. Experiments on CIFAR-10, CIFAR-100, and CINIC-10 demonstrate state-of-the-art accuracy (up to +1.21% on CIFAR-100), a 2.8x reduction in per-round transmission size, and robust performance under extreme non-IID conditions (α = 0.1), making DeepFedNAS practical for scalable, communication-constrained IoT federations. Source code: https://github.com/bostankhan6/DeepFedNAS

cs.LG↗
arXiv2026

Contextual Range-View Projection for 3D LiDAR Point Clouds

Range-view projection provides an efficient method for transforming 3D LiDAR point clouds into 2D range image representations, enabling effective processing with 2D deep learning models. However, a major challenge in this projection is the many-to-one conflict, where multiple 3D points are mapped onto the same pixel in the range image, requiring a selection strategy. Existing approaches typically retain the point with the smallest depth (closest to the LiDAR), disregarding semantic relevance and object structure, which leads to the loss of important contextual information. In this paper, we extend the depth-based selection rule by incorporating contextual information from both instance centers and class labels, introducing two mechanisms: \textit{Centerness-Aware Projection (CAP)} and \textit{Class-Weighted-Aware Projection (CWAP)}. In CAP, point depths are adjusted according to their distance from the instance center, thereby prioritizing central instance points over noisy boundary and background points. In CWAP, object classes are prioritized through user-defined weights, offering flexibility in the projection strategy. Our evaluations on the SemanticKITTI dataset show that CAP preserves more instance points during projection, achieving up to a 3.1\% mIoU improvement compared to the baseline. Furthermore, CWAP enhances the performance of targeted classes while having a negligible impact on the performance of other classes

cs.CV↗
arXiv2026

Correcting and Quantifying Systematic Errors in 3D Box Annotations for Autonomous Driving

Accurate ground truth annotations are critical to supervised learning and evaluating the performance of autonomous vehicle systems. These vehicles are typically equipped with active sensors, such as LiDAR, which scan the environment in predefined patterns. 3D box annotation based on data from such sensors is challenging in dynamic scenarios, where objects are observed at different timestamps, hence different positions. Without proper handling of this phenomenon, systematic errors are prone to being introduced in the box annotations. Our work is the first to discover such annotation errors in widely used, publicly available datasets. Through our novel offline estimation method, we correct the annotations so that they follow physically feasible trajectories and achieve spatial and temporal consistency with the sensor data. For the first time, we define metrics for this problem; and we evaluate our method on the Argoverse 2, MAN TruckScenes, and our proprietary datasets. Our approach increases the quality of box annotations by more than 17% in these datasets. Furthermore, we quantify the annotation errors in them and find that the original annotations are misplaced by up to 2.5 m, with highly dynamic objects being the most affected. Finally, we test the impact of the errors in benchmarking and find that the impact is larger than the improvements that state-of-the-art methods typically achieve with respect to the previous state-of-the-art methods; showing that accurate annotations are essential for correct interpretation of performance. Our code is available at https://github.com/alexandre-justo-miro/annotation-correction-3D-boxes.

cs.CV↗
arXiv2025

DeepVigor+: Scalable and Accurate Semi-Analytical Fault Resilience Analysis for Deep Neural Network

The growing exploitation of Machine Learning (ML) in safety-critical applications necessitates rigorous safety analysis. Hardware reliability assessment is a major concern with respect to measuring the level of safety in ML-based systems. Quantifying the reliability of emerging ML models, including Convolutional Neural Networks (CNNs), is highly complex due to their enormous size in terms of the number of parameters and computations. Conventionally, Fault Injection (FI) is applied to perform a reliability measurement. However, performing FI on modern-day CNNs is prohibitively time-consuming if an acceptable confidence level is to be achieved. To speed up FI for large CNNs, statistical FI (SFI) has been proposed, but its runtimes are still considerably long. In this work, we introduce DeepVigor+, a scalable, fast, and accurate semi-analytical method as an efficient alternative for reliability measurement in CNNs. DeepVigor+ implements a fault propagation analysis model and attempts to acquire Vulnerability Factors (VFs) as reliability metrics in an optimal way. The results indicate that DeepVigor+ obtains VFs for CNN models with an error less than $1\%$, i.e., the objective in SFI, but with $14.9$ up to $26.9$ times fewer simulations than the best-known state-of-the-art SFI. DeepVigor+ enables an accurate reliability analysis for large and deep CNNs within a few minutes, rather than achieving the same results in days or weeks.

cs.LG↗
arXiv2025

Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation

Post-Training Quantization (PTQ) reduces the memory footprint and computational overhead of deep neural networks by converting full-precision (FP) values into quantized and compressed data types. While PTQ is more cost-efficient than Quantization-Aware Training (QAT), it is highly susceptible to accuracy degradation under a low-bit quantization (LQ) regime (e.g., 2-bit). Affine transformation is a classical technique used to reduce the discrepancy between the information processed by a quantized model and that processed by its full-precision counterpart; however, we find that using plain affine transformation, which applies a uniform affine parameter set for all outputs, worsens the results in low-bit PTQ. To address this, we propose Cluster-based Affine Transformation (CAT), an error-reduction framework that employs cluster-specific parameters to align LQ outputs with FP counterparts. CAT refines LQ outputs with only a negligible number of additional parameters, without requiring fine-tuning of the model or quantization parameters. We further introduce a novel PTQ framework integrated with CAT. Experiments on ImageNet-1K show that this framework consistently outperforms prior PTQ methods across diverse architectures and LQ settings, achieving up to 53.18% Top-1 accuracy on W2A2 ResNet-18. Moreover, CAT enhances existing PTQ baselines by more than 3% when used as a plug-in. We plan to release our implementation alongside the publication of this paper.

cs.CV↗
arXiv2025

AxLLM: accelerator architecture for large language models with computation reuse capability

Large language models demand massive computational power and memory resources, posing significant challenges for efficient deployment. While quantization has been widely explored to reduce model size and computation, this paper demonstrates an additional benefit: quantization increases parameter locality, creating opportunities for computation reuse. Building on this insight, we propose AxLLM, a hardware accelerator architecture designed for quantized models. Axllm introduces a novel redundancy elimination technique that caches and reuses multiplication results for repeated weight values, substantially reducing redundant operations. The architecture features dual multiply and reuse pipelines, efficiently supporting both base models and LoRA fine-tuned models without altering parameters, retraining, or requiring offline preprocessing. Experimental results show that AxLLM achieves up to 90% reduction in computations, delivering 28% lower energy consumption and a 1.7x speedup over baseline execution. These results highlight Axllm as a scalable and efficient solution for accelerating LLMs on specialized hardware.

cs.AR↗
arXiv2025

ProARD: progressive adversarial robustness distillation: provide wide range of robust students

Adversarial Robustness Distillation (ARD) has emerged as an effective method to enhance the robustness of lightweight deep neural networks against adversarial attacks. Current ARD approaches have leveraged a large robust teacher network to train one robust lightweight student. However, due to the diverse range of edge devices and resource constraints, current approaches require training a new student network from scratch to meet specific constraints, leading to substantial computational costs and increased CO2 emissions. This paper proposes Progressive Adversarial Robustness Distillation (ProARD), enabling the efficient one-time training of a dynamic network that supports a diverse range of accurate and robust student networks without requiring retraining. We first make a dynamic deep neural network based on dynamic layers by encompassing variations in width, depth, and expansion in each design stage to support a wide range of architectures. Then, we consider the student network with the largest size as the dynamic teacher network. ProARD trains this dynamic network using a weight-sharing mechanism to jointly optimize the dynamic teacher network and its internal student networks. However, due to the high computational cost of calculating exact gradients for all the students within the dynamic network, a sampling mechanism is required to select a subset of students. We show that random student sampling in each iteration fails to produce accurate and robust students.

cs.LG↗
arXiv2025

Exploring FMCW Radars and Feature Maps for Activity Recognition: A Benchmark Study

Human Activity Recognition has gained significant attention due to its diverse applications, including ambient assisted living and remote sensing. Wearable sensor-based solutions often suffer from user discomfort and reliability issues, while video-based methods raise privacy concerns and perform poorly in low-light conditions or long ranges. This study introduces a Frequency-Modulated Continuous Wave radar-based framework for human activity recognition, leveraging a 60 GHz radar and multi-dimensional feature maps. Unlike conventional approaches that process feature maps as images, this study feeds multi-dimensional feature maps -- Range-Doppler, Range-Azimuth, and Range-Elevation -- as data vectors directly into the machine learning (SVM, MLP) and deep learning (CNN, LSTM, ConvLSTM) models, preserving the spatial and temporal structures of the data. These features were extracted from a novel dataset with seven activity classes and validated using two different validation approaches. The ConvLSTM model outperformed conventional machine learning and deep learning models, achieving an accuracy of 90.51% and an F1-score of 87.31% on cross-scene validation and an accuracy of 89.56% and an F1-score of 87.15% on leave-one-person-out cross-validation. The results highlight the approach's potential for scalable, non-intrusive, and privacy-preserving activity monitoring in real-world scenarios.

cs.ET↗
arXiv2024

Contrastive Learning for Lane Detection via cross-similarity

Detecting lane markings in road scenes poses a challenge due to their intricate nature, which is susceptible to unfavorable conditions. While lane markings have strong shape priors, their visibility is easily compromised by lighting conditions, occlusions by other vehicles or pedestrians, and fading of colors over time. The detection process is further complicated by the presence of several lane shapes and natural variations, necessitating large amounts of data to train a robust lane detection model capable of handling various scenarios. In this paper, we present a novel self-supervised learning method termed Contrastive Learning for Lane Detection via cross-similarity (CLLD) to enhance the resilience of lane detection models in real-world scenarios, particularly when the visibility of lanes is compromised. CLLD introduces a contrastive learning (CL) method that assesses the similarity of local features within the global context of the input image. It uses the surrounding information to predict lane markings. This is achieved by integrating local feature contrastive learning with our proposed cross-similar operation. The local feature CL concentrates on extracting features from small patches, a necessity for accurately localizing lane segments. Meanwhile, cross-similarity captures global features, enabling the detection of obscured lane segments based on their surroundings. We enhance cross-similarity by randomly masking portions of input images in the process of augmentation. Extensive experiments on TuSimple and CuLane benchmarks demonstrate that CLLD outperforms SOTA contrastive learning methods, particularly in visibility-impairing conditions like shadows, while it also delivers comparable results under normal conditions. Compared to supervised learning, CLLD still excels in challenging scenarios such as shadows and crowded scenes, which are common in real-world driving.

cs.CV↗
arXiv2024

ProAct: Progressive Training for Hybrid Clipped Activation Function to Enhance Resilience of DNNs

Deep Neural Networks (DNNs) are extensively employed in safety-critical applications where ensuring hardware reliability is a primary concern. To enhance the reliability of DNNs against hardware faults, activation restriction techniques significantly mitigate the fault effects at the DNN structure level, irrespective of accelerator architectures. State-of-the-art methods offer either neuron-wise or layer-wise clipping activation functions. They attempt to determine optimal clipping thresholds using heuristic and learning-based approaches. Layer-wise clipped activation functions cannot preserve DNNs resilience at high bit error rates. On the other hand, neuron-wise clipping activation functions introduce considerable memory overhead due to the addition of parameters, which increases their vulnerability to faults. Moreover, the heuristic-based optimization approach demands numerous fault injections during the search process, resulting in time-consuming threshold identification. On the other hand, learning-based techniques that train thresholds for entire layers concurrently often yield sub-optimal results. In this work, first, we demonstrate that it is not essential to incorporate neuron-wise activation functions throughout all layers in DNNs. Then, we propose a hybrid clipped activation function that integrates neuron-wise and layer-wise methods that apply neuron-wise clipping only in the last layer of DNNs. Additionally, to attain optimal thresholds in the clipping activation function, we introduce ProAct, a progressive training methodology. This approach iteratively trains the thresholds on a layer-by-layer basis, aiming to obtain optimal threshold values in each layer separately.

cs.LG↗
arXiv2024

Cost-Effective Fault Tolerance for CNNs Using Parameter Vulnerability Based Hardening and Pruning

Convolutional Neural Networks (CNNs) have become integral in safety-critical applications, thus raising concerns about their fault tolerance. Conventional hardware-dependent fault tolerance methods, such as Triple Modular Redundancy (TMR), are computationally expensive, imposing a remarkable overhead on CNNs. Whereas fault tolerance techniques can be applied either at the hardware level or at the model levels, the latter provides more flexibility without sacrificing generality. This paper introduces a model-level hardening approach for CNNs by integrating error correction directly into the neural networks. The approach is hardware-agnostic and does not require any changes to the underlying accelerator device. Analyzing the vulnerability of parameters enables the duplication of selective filters/neurons so that their output channels are effectively corrected with an efficient and robust correction layer. The proposed method demonstrates fault resilience nearly equivalent to TMR-based correction but with significantly reduced overhead. Nevertheless, there exists an inherent overhead to the baseline CNNs. To tackle this issue, a cost-effective parameter vulnerability based pruning technique is proposed that outperforms the conventional pruning method, yielding smaller networks with a negligible accuracy loss. Remarkably, the hardened pruned CNNs perform up to 24\% faster than the hardened un-pruned ones.

cs.LG↗
arXiv2024

TrajectoryNAS: A Neural Architecture Search for Trajectory Prediction

Autonomous driving systems are a rapidly evolving technology that enables driverless car production. Trajectory prediction is a critical component of autonomous driving systems, enabling cars to anticipate the movements of surrounding objects for safe navigation. Trajectory prediction using Lidar point-cloud data performs better than 2D images due to providing 3D information. However, processing point-cloud data is more complicated and time-consuming than 2D images. Hence, state-of-the-art 3D trajectory predictions using point-cloud data suffer from slow and erroneous predictions. This paper introduces TrajectoryNAS, a pioneering method that focuses on utilizing point cloud data for trajectory prediction. By leveraging Neural Architecture Search (NAS), TrajectoryNAS automates the design of trajectory prediction models, encompassing object detection, tracking, and forecasting in a cohesive manner. This approach not only addresses the complex interdependencies among these tasks but also emphasizes the importance of accuracy and efficiency in trajectory modeling. Through empirical studies, TrajectoryNAS demonstrates its effectiveness in enhancing the performance of autonomous driving systems, marking a significant advancement in the field.Experimental results reveal that TrajcetoryNAS yield a minimum of 4.8 higger accuracy and 1.1* lower latency over competing methods on the NuScenes dataset.

cs.CV↗
arXiv2024

SAFFIRA: a Framework for Assessing the Reliability of Systolic-Array-Based DNN Accelerators

Systolic array has emerged as a prominent architecture for Deep Neural Network (DNN) hardware accelerators, providing high-throughput and low-latency performance essential for deploying DNNs across diverse applications. However, when used in safety-critical applications, reliability assessment is mandatory to guarantee the correct behavior of DNN accelerators. While fault injection stands out as a well-established practical and robust method for reliability assessment, it is still a very time-consuming process. This paper addresses the time efficiency issue by introducing a novel hierarchical software-based hardware-aware fault injection strategy tailored for systolic array-based DNN accelerators.

cs.AI↗
arXiv2024

Exploration of Activation Fault Reliability in Quantized Systolic Array-Based DNN Accelerators

The stringent requirements for the Deep Neural Networks (DNNs) accelerator's reliability stand along with the need for reducing the computational burden on the hardware platforms, i.e. reducing the energy consumption and execution time as well as increasing the efficiency of DNN accelerators. Moreover, the growing demand for specialized DNN accelerators with tailored requirements, particularly for safety-critical applications, necessitates a comprehensive design space exploration to enable the development of efficient and robust accelerators that meet those requirements. Therefore, the trade-off between hardware performance, i.e. area and delay, and the reliability of the DNN accelerator implementation becomes critical and requires tools for analysis. This paper presents a comprehensive methodology for exploring and enabling a holistic assessment of the trilateral impact of quantization on model accuracy, activation fault reliability, and hardware efficiency. A fully automated framework is introduced that is capable of applying various quantization-aware techniques, fault injection, and hardware implementation, thus enabling the measurement of hardware parameters. Moreover, this paper proposes a novel lightweight protection technique integrated within the framework to ensure the dependable deployment of the final systolic-array-based FPGA implementation. The experiments on established benchmarks demonstrate the analysis flow and the profound implications of quantization on reliability, hardware performance, and network accuracy, particularly concerning the transient faults in the network's activations.

cs.AR↗
arXiv2023

DASS: Differentiable Architecture Search for Sparse neural networks

The deployment of Deep Neural Networks (DNNs) on edge devices is hindered by the substantial gap between performance requirements and available processing power. While recent research has made significant strides in developing pruning methods to build a sparse network for reducing the computing overhead of DNNs, there remains considerable accuracy loss, especially at high pruning ratios. We find that the architectures designed for dense networks by differentiable architecture search methods are ineffective when pruning mechanisms are applied to them. The main reason is that the current method does not support sparse architectures in their search space and uses a search objective that is made for dense networks and does not pay any attention to sparsity. In this paper, we propose a new method to search for sparsity-friendly neural architectures. We do this by adding two new sparse operations to the search space and modifying the search objective. We propose two novel parametric SparseConv and SparseLinear operations in order to expand the search space to include sparse operations. In particular, these operations make a flexible search space due to using sparse parametric versions of linear and convolution operations. The proposed search objective lets us train the architecture based on the sparsity of the search space operations. Quantitative analyses demonstrate that our search architectures outperform those used in the stateof-the-art sparse networks on the CIFAR-10 and ImageNet datasets. In terms of performance and hardware effectiveness, DASS increases the accuracy of the sparse version of MobileNet-v2 from 73.44% to 81.35% (+7.91% improvement) with 3.87x faster inference time.

cs.CV↗