Article

GatherNet: The Lightest Convolutional Neural Network Architecture So far

2024-07-03

Abstract excerpt

<title>Abstract</title> <p>It is generally difficult to establish convolutional neural networks with many operations on mobile devices due to their limited memory and computation resources. This paper proposes a novel Gather module that combines depthwise separable convolution and standard convolution with Ghost module to generate feature maps cheaply and efficiently and uses channel shuffle to rearrange these le...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 7df8ffc9-7fbd-5b14-bd5b-09584011a043
DOI: 10.21203/rs.3.rs-4580378/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

GatherNet: The Lightest Convolutional Neural Network Architecture So farDOI 10.21203/rs.3.rs-4580378/v1Read

Symbiotic Convolution Block (SCB): An Implicit Feature Recalibration without Attention-Mechanism for Efficient CNNs in Image ClassificationSemantic proximity Read

EyeDx: A Scalable and Interpretable Multitask Deep Learning Framework for Comprehensive Ocular Disease Detection in Fundus ImagesSemantic proximity Read

Deep Learning Framework for Multiclass Detection of Ocular Diseases in Fundus ImagesSemantic proximity Read

Improved Diabetic Retinopathy Severity Classification Using Squeeze-and-excitation and Sparse Light Weight Multi-level Attention U-net With Transfer Learning From XceptionSemantic proximity Read

EDNet-20: Enhancing Multi-Label Ocular Disease Detection through Deep Learning OptimizationSemantic proximity Read

Deep Learning Framework for Automated Goblet Cell Density Analysis in In-Vivo Rabbit ConjunctivaSemantic proximity Read

Deep Learning based Intraretinal Layer Segmentation using Cascaded Compressed U-NetSemantic proximity Read

Eye Disease Classification by Advanced Deep Transfer Learning System Using Resnet50 & XceptionSemantic proximity Read

Automatic Classification of Heterogeneous Slit-Illumination Images Using an Ensemble of Cost-Sensitive Convolutional Neural NetworksSemantic proximity Read

Demystifying CNN with Mathematical Insights: A Prelude with Application to an AI-based Sustainable Solution for Diabetic Retinopathy DiagnosisSemantic proximity Read

EfficientNet-B7-Based Transfer Learning with Image Preprocessing and Morphological Feature Fusion for Glaucoma DetectionSemantic proximity Read

Multi-task Deep Learning for Glaucoma Detection From Color Fundus ImagesSemantic proximity Read