L. A. Dunbar
YOU?
Author Swipe
View article: EFLOP: A Sparsity-Aware Metric for Evaluating Computational Cost in Spiking and Non-Spiking Neural Networks
EFLOP: A Sparsity-Aware Metric for Evaluating Computational Cost in Spiking and Non-Spiking Neural Networks Open
Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both ANNs and SNNs have been proposed as candidates for these tasks …
View article: SAND: One-Shot Feature Selection with Additive Noise Distortion
SAND: One-Shot Feature Selection with Additive Noise Distortion Open
Feature selection is a critical step in data-driven applications, reducing input dimensionality to enhance learning accuracy, computational efficiency, and interpretability. Existing state-of-the-art methods often require post-selection re…
View article: Hierarchical Training of Deep Neural Networks Using Early Exiting
Hierarchical Training of Deep Neural Networks Using Early Exiting Open
Deep neural networks (DNNs) provide state-of-the-art accuracy for vision tasks, but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increa…
View article: Deploying a Convolutional Neural Network on Edge MCU and Neuromorphic Hardware Platforms
Deploying a Convolutional Neural Network on Edge MCU and Neuromorphic Hardware Platforms Open
The rapid development of embedded technologies in recent decades has led to the advent of dedicated inference platforms for deep learning. However, unlike development libraries for the algorithms, hardware deployment is highly fragmented i…
View article: Hierarchical Training of Deep Neural Networks Using Early Exiting
Hierarchical Training of Deep Neural Networks Using Early Exiting Open
Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases comm…
View article: Privacy-Preserving Image Acquisition for Neural Vision Systems
Privacy-Preserving Image Acquisition for Neural Vision Systems Open
Preserving privacy is a growing concern in our society where cameras are ubiquitous. In this work, we propose a trainable image acquisition method that removes the sensitive information in the optical domain before it reaches the image sen…
View article: Adaptation of MobileNetV2 for Face Detection on Ultra-Low Power Platform
Adaptation of MobileNetV2 for Face Detection on Ultra-Low Power Platform Open
Designing Deep Neural Networks (DNNs) running on edge hardware remains a challenge. Standard designs have been adopted by the community to facilitate the deployment of Neural Network models. However, not much emphasis is put on adapting th…
View article: Table of Contents
Table of Contents Open
View article: Adaptation of MobileNetV2 for Face Detection on Ultra-Low Power Platform
Adaptation of MobileNetV2 for Face Detection on Ultra-Low Power Platform Open
Designing Deep Neural Networks (DNNs) running on edge hardware remains a challenge. Standard designs have been adopted by the community to facilitate the deployment of Neural Network models. However, not much emphasis is put on adapting th…
View article: Optimizing the Consumption of Spiking Neural Networks with Activity Regularization
Optimizing the Consumption of Spiking Neural Networks with Activity Regularization Open
Reducing energy consumption is a critical point for neural network models running on edge devices. In this regard, reducing the number of multiply-accumulate (MAC) operations of Deep Neural Networks (DNNs) running on edge hardware accelera…
View article: Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo
Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo Open
The problem of estimating a surface shape from its observed reflectance properties still remains a challenging task in computer vision. The presence of global illumination effects such as inter-reflections or cast shadows makes the task pa…
View article: Defect segmentation for multi-illumination quality control systems
Defect segmentation for multi-illumination quality control systems Open
Thanks to recent advancements in image processing and deep learning techniques, visual surface inspection in production lines has become an automated process as long as all the defects are visible in a single or a few images. However, it i…
View article: CSEM-MISD - CSEM's Multi-Illumination Surface Defect Detection Dataset
CSEM-MISD - CSEM's Multi-Illumination Surface Defect Detection Dataset Open
In automated surface visual inspection, it is often necessary to capture the inspected part under many different illumination conditions to capture all the defects. To address this issue, at CSEM we have acquired a real-world multi-illumin…
View article: CSEM-MISD - CSEM's Multi-Illumination Surface Defect Detection Dataset
CSEM-MISD - CSEM's Multi-Illumination Surface Defect Detection Dataset Open
In automated surface visual inspection, it is often necessary to capture the inspected part under many different illumination conditions to capture all the defects. To address this issue, at CSEM we have acquired a real-world multi-illumin…
View article: CSEM-MISD - CSEM's Multi-Illumination Surface Defect Detection Dataset
CSEM-MISD - CSEM's Multi-Illumination Surface Defect Detection Dataset Open
In automated surface visual inspection, it is often necessary to capture the inspected part under many different illumination conditions to capture all the defects. To address this issue, at CSEM we have acquired a real-world multi-illumin…
View article: Efficient Blind-Spot Neural Network Architecture for Image Denoising
Efficient Blind-Spot Neural Network Architecture for Image Denoising Open
Image denoising is an essential tool in computational photography. Standard\ndenoising techniques, which use deep neural networks at their core, require\npairs of clean and noisy images for its training. If we do not possess the\nclean sam…
View article: Learning Generative Models using Denoising Density Estimators
Learning Generative Models using Denoising Density Estimators Open
Learning probabilistic models that can estimate the density of a given set of samples, and generate samples from that density, is one of the fundamental challenges in unsupervised machine learning. We introduce a new generative model based…
View article: Image Restoration using Plug-and-Play CNN MAP Denoisers
Image Restoration using Plug-and-Play CNN MAP Denoisers Open
Plug-and-play denoisers can be used to perform generic image restoration tasks independent of the degradation type. These methods build on the fact that the Maximum a Posteriori (MAP) optimization can be solved using smaller sub-problems, …
View article: Plasmonic nanohole arrays on Si-Ge heterostructures: an approach for integrated biosensors
Plasmonic nanohole arrays on Si-Ge heterostructures: an approach for integrated biosensors Open
Nanohole array surface plasmon resonance (SPR) sensors offer a promising platform for high-throughput label-free biosensing. Integrating nanohole arrays with group-IV semiconductor photodetectors could enable low-cost and disposable biosen…
View article: Integrated angular tracking and plasmonic membrane surfaces for a point of a care refractive index sensor
Integrated angular tracking and plasmonic membrane surfaces for a point of a care refractive index sensor Open
We present an optical system which integrates a plasmonic sensing surface and an angular tracking system to enable a compact refractive index measurement. A refractive index change at the surface of the sensing membrane causes a change in …
View article: Venous thromboembolism rates in patients with lower limb immobilization after Achilles tendon injury are unchanged after the introduction of prophylactic aspirin: audit
Venous thromboembolism rates in patients with lower limb immobilization after Achilles tendon injury are unchanged after the introduction of prophylactic aspirin: audit Open
ESSENTIALS: We audited venous thromboembolism (VTE) in Achilles injuries after the use of prophylactic aspirin. We audited 218 patients with Achilles injury requiring lower limb immobilization for ≥ 1 week. Fourteen patients (6.4%, 95% CI …