arXiv subjects

Amirali Baniasadi

Publications and source records attributed to Amirali Baniasadi.

13 recordsLinked to original sources

arXiv2025

PrunedCaps: A Case For Primary Capsules Discrimination

Capsule Networks (CapsNets) are a generation of image classifiers with proven advantages over Convolutional Neural Networks (CNNs). Better robustness to affine transformation and overlapping image detection are some of the benefits associated with CapsNets. However, CapsNets cannot be classified as resource-efficient deep learning architecture due to the high number of Primary Capsules (PCs). In addition, CapsNets' training and testing are slow and resource hungry. This paper investigates the possibility of Primary Capsules pruning in CapsNets on MNIST handwritten digits, Fashion-MNIST, CIFAR-10, and SVHN datasets. We show that a pruned version of CapsNet performs up to 9.90 times faster than the conventional architecture by removing 95 percent of Capsules without a loss of accuracy. Also, our pruned architecture saves on more than 95.36 percent of floating-point operations in the dynamic routing stage of the architecture. Moreover, we provide insight into why some datasets benefit significantly from pruning while others fall behind.

cs.CV↗

arXiv2025

DL-CapsNet: A Deep and Light Capsule Network

Capsule Network (CapsNet) is among the promising classifiers and a possible successor of the classifiers built based on Convolutional Neural Network (CNN). CapsNet is more accurate than CNNs in detecting images with overlapping categories and those with applied affine transformations. In this work, we propose a deep variant of CapsNet consisting of several capsule layers. In addition, we design the Capsule Summarization layer to reduce the complexity by reducing the number of parameters. DL-CapsNet, while being highly accurate, employs a small number of parameters and delivers faster training and inference. DL-CapsNet can process complex datasets with a high number of categories.

cs.CV↗

arXiv2025

LE-CapsNet: A Light and Enhanced Capsule Network

Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.3% accuracy on the AffNIST dataset (compared to CapsNet 90.52%).

cs.CV↗

arXiv2025

Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network

A Capsule Network (CapsNet) is a relatively new classifier and one of the possible successors of Convolutional Neural Networks (CNNs). CapsNet maintains the spatial hierarchies between the features and outperforms CNNs at classifying images including overlapping categories. Even though CapsNet works well on small-scale datasets such as MNIST, it fails to achieve a similar level of performance on more complicated datasets and real applications. In addition, CapsNet is slow compared to CNNs when performing the same task and relies on a higher number of parameters. In this work, we introduce Convolutional Fully-Connected Capsule Network (CFC-CapsNet) to address the shortcomings of CapsNet by creating capsules using a different method. We introduce a new layer (CFC layer) as an alternative solution to creating capsules. CFC-CapsNet produces fewer, yet more powerful capsules resulting in higher network accuracy. Our experiments show that CFC-CapsNet achieves competitive accuracy, faster training and inference and uses less number of parameters on the CIFAR-10, SVHN and Fashion-MNIST datasets compared to conventional CapsNet.

cs.CV↗

arXiv2025

Quick-CapsNet (QCN): A fast alternative to Capsule Networks

The basic computational unit in Capsule Network (CapsNet) is a capsule (vs. neurons in Convolutional Neural Networks (CNNs)). A capsule is a set of neurons, which form a vector. CapsNet is used for supervised classification of data and has achieved state-of-the-art accuracy on MNIST digit recognition dataset, outperforming conventional CNNs in detecting overlapping digits. Moreover, CapsNet shows higher robustness towards affine transformation when compared to CNNs for MNIST datasets. One of the drawbacks of CapsNet, however, is slow training and testing. This can be a bottleneck for applications that require a fast network, especially during inference. In this work, we introduce Quick-CapsNet (QCN) as a fast alternative to CapsNet, which can be a starting point to develop CapsNet for fast real-time applications. QCN builds on producing a fewer number of capsules, which results in a faster network. QCN achieves this at the cost of marginal loss in accuracy. Inference is 5x faster on MNIST, F-MNIST, SVHN and Cifar-10 datasets. We also further enhanced QCN by employing a more powerful decoder instead of the default decoder to further improve QCN.

cs.CV↗

arXiv2025

Generating Synthetic Contrast-Enhanced Chest CT Images from Non-Contrast Scans Using Slice-Consistent Brownian Bridge Diffusion Network

Contrast-enhanced computed tomography (CT) imaging is essential for diagnosing and monitoring thoracic diseases, including aortic pathologies. However, contrast agents pose risks such as nephrotoxicity and allergic-like reactions. The ability to generate high-fidelity synthetic contrast-enhanced CT angiography (CTA) images without contrast administration would be transformative, enhancing patient safety and accessibility while reducing healthcare costs. In this study, we propose the first bridge diffusion-based solution for synthesizing contrast-enhanced CTA images from non-contrast CT scans. Our approach builds on the Slice-Consistent Brownian Bridge Diffusion Model (SC-BBDM), leveraging its ability to model complex mappings while maintaining consistency across slices. Unlike conventional slice-wise synthesis methods, our framework preserves full 3D anatomical integrity while operating in a high-resolution 2D fashion, allowing seamless volumetric interpretation under a low memory budget. To ensure robust spatial alignment, we implement a comprehensive preprocessing pipeline that includes resampling, registration using the Symmetric Normalization method, and a sophisticated dilated segmentation mask to extract the aorta and surrounding structures. We create two datasets from the Coltea-Lung dataset: one containing only the aorta and another including both the aorta and heart, enabling a detailed analysis of anatomical context. We compare our approach against baseline methods on both datasets, demonstrating its effectiveness in preserving vascular structures while enhancing contrast fidelity.

eess.IV↗

arXiv2025

A Review on Sound Source Localization in Robotics: Focusing on Deep Learning Methods

Sound source localization (SSL) adds a spatial dimension to auditory perception, allowing a system to pinpoint the origin of speech, machinery noise, warning tones, or other acoustic events, capabilities that facilitate robot navigation, human-machine dialogue, and condition monitoring. While existing surveys provide valuable historical context, they typically address general audio applications and do not fully account for robotic constraints or the latest advancements in deep learning. This review addresses these gaps by offering a robotics-focused synthesis, emphasizing recent progress in deep learning methodologies. We start by reviewing classical methods such as Time Difference of Arrival (TDOA), beamforming, Steered-Response Power (SRP), and subspace analysis. Subsequently, we delve into modern machine learning (ML) and deep learning (DL) approaches, discussing traditional ML and neural networks (NNs), convolutional neural networks (CNNs), convolutional recurrent neural networks (CRNNs), and emerging attention-based architectures. The data and training strategy that are the two cornerstones of DL-based SSL are explored. Studies are further categorized by robot types and application domains to facilitate researchers in identifying relevant work for their specific contexts. Finally, we highlight the current challenges in SSL works in general, regarding environmental robustness, sound source multiplicity, and specific implementation constraints in robotics, as well as data and learning strategies in DL-based SSL. Also, we sketch promising directions to offer an actionable roadmap toward robust, adaptable, efficient, and explainable DL-based SSL for next-generation robots.

cs.RO↗

arXiv2023

PDR-CapsNet: an Energy-Efficient Parallel Approach to Dynamic Routing in Capsule Networks

Convolutional Neural Networks (CNNs) have produced state-of-the-art results for image classification tasks. However, they are limited in their ability to handle rotational and viewpoint variations due to information loss in max-pooling layers. Capsule Networks (CapsNets) employ a computationally-expensive iterative process referred to as dynamic routing to address these issues. CapsNets, however, often fall short on complex datasets and require more computational resources than CNNs. To overcome these challenges, we introduce the Parallel Dynamic Routing CapsNet (PDR-CapsNet), a deeper and more energy-efficient alternative to CapsNet that offers superior performance, less energy consumption, and lower overfitting rates. By leveraging a parallelization strategy, PDR-CapsNet mitigates the computational complexity of CapsNet and increases throughput, efficiently using hardware resources. As a result, we achieve 83.55\% accuracy while requiring 87.26\% fewer parameters, 32.27\% and 47.40\% fewer MACs, and Flops, achieving 3x faster inference and 7.29J less energy consumption on a 2080Ti GPU with 11GB VRAM compared to CapsNet and for the CIFAR-10 dataset.

cs.LG↗

arXiv2021

Using Silent Writes in Low-Power Traffic-Aware ECC

Using Error Detection Code (EDC) and Error Correction Code (ECC) is a noteworthy way to increase cache memories robustness against soft errors. EDC enables detecting errors in cache memory while ECC is used to correct erroneous cache blocks. ECCs are often costly as they impose considerable area and energy overhead on cache memory. Reducing this overhead has been the subject of many studies. In particular, a previous study has suggested mapping ECC to the main memory at the expense of high cache traffic and energy. A major source of this excessive traffic and energy is the high frequency of cache writes. In this work, we show that a significant portion of cache writes are silent, i.e., they write the same data already existing. We build on this observation and introduce Traffic-aware ECC (or simply TCC). TCC detects silent writes by an efficient mechanism. Once such writes are detected updating their ECC is avoided effectively reducing L2 cache traffic and access frequency. Using our solution, we reduce L2 cache access frequency by 8% while maintaining performance. We reduce L2 cache dynamic and overall cache energy by up to 32% and 8%, respectively. Furthermore, TCC reduces L2 cache miss rate by 3%.

cs.PF↗

arXiv2020

Quantum Annealing Approaches to the Phase-Unwrapping Problem in Synthetic-Aperture Radar Imaging

The focus of this work is to explore the use of quantum annealing solvers for the problem of phase unwrapping of synthetic aperture radar (SAR) images. Although solutions to this problem exist based on network programming, these techniques do not scale well to larger-sized images. Our approach involves formulating the problem as a quadratic unconstrained binary optimization (QUBO) problem, which can be solved using a quantum annealer. Given that present embodiments of quantum annealers remain limited in the number of qubits they possess, we decompose the problem into a set of subproblems that can be solved individually. These individual solutions are close to optimal up to an integer constant, with one constant per sub-image. In a second phase, these integer constants are determined as a solution to yet another QUBO problem. We test our approach with a variety of software-based QUBO solvers and on a variety of images, both synthetic and real. Additionally, we experiment using D-Wave Systems's quantum annealer, the D-Wave 2000Q. The software-based solvers obtain high-quality solutions comparable to state-of-the-art phase-unwrapping solvers. We are currently working on optimally mapping the problem onto the restricted topology of the quantum annealer to improve the quality of the solution.

cs.CV↗

arXiv2014

IPMACC: Open Source OpenACC to CUDA/OpenCL Translator

In this paper we introduce IPMACC, a framework for translating OpenACC applications to CUDA or OpenCL. IPMACC is composed of set of translators translating OpenACC for C applications to CUDA or OpenCL. The framework uses the system compiler (e.g. nvcc) for generating final accelerator's binary. The framework can be used for extending the OpenACC API, executing OpenACC applications, or obtaining CUDA or OpenCL code which is equivalent to OpenACC code. We verify correctness of our framework under several benchmarks included from Rodinia Benchmark Suit and CUDA SDK. We also compare the performance of CUDA version of the benchmarks to OpenACC version which is compiled by our framework. By comparing CUDA and OpenACC versions, we discuss the limitations of OpenACC in achieving a performance near to highly-optimized CUDA version.

cs.PL↗

arXiv2012

Dynamic Warp Resizing in High-Performance SIMT

Modern GPUs synchronize threads grouped in a warp at every instruction. These results in improving SIMD efficiency and makes sharing fetch and decode resources possible. The number of threads included in each warp (or warp size) affects divergence, synchronization overhead and the efficiency of memory access coalescing. Small warps reduce the performance penalty associated with branch and memory divergence at the expense of a reduction in memory coalescing. Large warps enhance memory coalescing significantly but also increase branch and memory divergence. Dynamic workload behavior, including branch/memory divergence and coalescing, is an important factor in determining the warp size returning best performance. Optimal warp size can vary from one workload to another or from one program phase to the next. Based on this observation, we propose Dynamic Warp Resizing (DWR). DWR takes innovative microarchitectural steps to adjust warp size during runtime and according to program characteristics. DWR outperforms static warp size decisions, up to 1.7X to 2.28X, while imposing less than 1% area overhead. We investigate various alternative configurations and show that DWR performs better for narrower SIMD and larger caches.

cs.AR↗

arXiv2012

Investigating Warp Size Impact in GPUs

There are a number of design decisions that impact a GPU's performance. Among such decisions deciding the right warp size can deeply influence the rest of the design. Small warps reduce the performance penalty associated with branch divergence at the expense of a reduction in memory coalescing. Large warps enhance memory coalescing significantly but also increase branch divergence. This leaves designers with two choices: use a small warps and invest in finding new solutions to enhance coalescing or use large warps and address branch divergence employing effective control-flow solutions. In this work our goal is to investigate the answer to this question. We analyze warp size impact on memory coalescing and branch divergence. We use our findings to study two machines: a GPU using small warps but equipped with excellent memory coalescing (SW+) and a GPU using large warps but employing an MIMD engine immune from control-flow costs (LW+). Our evaluations show that building coalescing-enhanced small warp GPUs is a better approach compared to pursuing a control-flow enhanced large warp GPU.

cs.AR↗