Related papers: Hardware-Aware Automated Neural Minimization for P…

Deformable image registration is a fundamental step for medical image analysis. Recently, transformers have been used for registration and outperformed Convolutional Neural Networks (CNNs). Transformers can capture long-range dependence…

State-of-the-art computer vision tasks, like monocular depth estimation (MDE), rely heavily on large, modern Transformer-based architectures. However, their application in safety-critical domains demands reliable predictive performance and…

We show how perceptual embeddings of the visual system can be constructed at inference-time with no training data or deep neural network features. Our perceptual embeddings are solutions to a weighted least squares (WLS) problem, defined at…

In this work, we use artificial neural networks (ANNs) to recognize the material composition, sizes of nanoparticles and their concentrations in different media with high accuracy, solely from the absorbance spectrum of a macroscopic…

Machine learning (ML) is moving towards edge devices. However, ML models with high computational demands and energy consumption pose challenges for ML inference in resource-constrained environments, such as the deep sea. To address these…

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

Today, large language models have demonstrated their strengths in various tasks ranging from reasoning, code generation, and complex problem solving. However, this advancement comes with a high computational cost and memory requirements,…

An exponential increase in the performance of silicon microelectronics and the demand to manufacture in great volumes has created an ecosystem that requires increasingly complex tools to fabricate and characterize the next generation of…

Photoacoustic imaging (PAI) can image high-resolution structures of clinical interest such as vascularity in cancerous tumor monitoring. When imaging human subjects, geometric restrictions force limited-view data retrieval causing imaging…

Our long term goal is to execute General Purpose computation on homogeneous computing media consisting of millions of small identical Processing Elements (PE) communicating locally. We proceed by simulating the Self-Development of a Network…

Flexible piezoelectric devices made of polymeric materials are widely used for micro- and nano-electro-mechanical systems. In particular, numerous recent applications concern energy harvesting. Due to the importance of computational…

The recent surge of automation in the retail industries has rapidly increased demand for applying deep learning models on mobile devices. To make the deep learning models real-time on-device, a compact efficient network becomes inevitable.…

INTRODUCTION | Fully supervised 3D segmentation of high-resolution ex vivo MRI is limited by the prohibitive cost of volumetric annotation, forcing reliance on sparse 2D slices. Weakly supervised Sparse-to-Dense frameworks bridge this gap,…

Artificial Neural Networks (ANNs) have emerged as hot topics in the research community. Despite the success of ANNs, it is challenging to train and deploy modern ANNs on commodity hardware due to the ever-increasing model size and the…

Fourier Ptychographic Microscopy (FPM) is a computational technique that achieves a large space-bandwidth product imaging. It addresses the challenge of balancing a large field of view and high resolution by fusing information from multiple…

Convolutional Neural Networks have achieved unprecedented success in image classification, recognition, or detection applications. However, their large-scale deployment in embedded devices is still limited by the huge computational…

Although Vision Transformers (ViTs) have recently advanced computer vision tasks significantly, an important real-world problem was overlooked: adapting to variable input resolutions. Typically, images are resized to a fixed resolution,…

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

Recently, researchers have utilized neural networks to accurately solve partial differential equations (PDEs), enabling the mesh-free method for scientific computation. Unfortunately, the network performance drops when encountering a high…

We explore unique considerations involved in fitting ML models to data with very high precision, as is often required for science applications. We empirically compare various function approximation methods and study how they scale with…