IEEE

An Energy-Efficient Image Deblurring Accelerator With Quad-Base-Quad-Scale Quantized Format and Layer Normalization-Aware Optimization

Abstract: This brief proposes a novel data-format-based image deblurring accelerator with layer normalization and UNet architecture optimization for mobile cameras. As the demand for photography in ...
IEEE

Volumetric Hadamard Normalization for Synthetic Aperture Sonar Sub-Bottom Target Classification

Image normalization strategies for 3-D synthetic aperture sonar (SAS) is a relatively underexplored area for target classification leveraging convolutional neural networks (CNNs). For 3-D SAS data, ...
Frontiers

Exploring potential imaging biomarkers for ischemic retinal vein occlusion: insights from fundus autofluorescence and optical coherence tomography

Purpose: This study aimed to investigate the characteristics of macular edema observed by fundus autofluorescence (FAF) and to analyze noninvasive indicators of ischemia in retinal vein occlusion (RVO ...
eLife

New idtracker.ai: rethinking multi-animal tracking as a representation learning problem to increase accuracy and reduce tracking times

Each dot represents an image of an animal from the video. As training progresses, clusters corresponding to individual animals become clearer, plotted at training with 0, 2,000, 4,000 and 15,000 ...