BEVFormer v2: Adapting Modern Image Backbones to

We present a novel bird''s-eye-view (BEV) detector with perspective supervision, which converges faster and better

DB-SegNet: optimized framework for glaucoma detection and optic

To address these issues, this study introduces DB-SegNet, an advanced diagnostic framework designed to enhance

Evaluating the Impact of Backbone Networks and Input

This study employs a top-down pose estimation framework to evaluate the effect of various backbone architectures on

Using Deep Learning to Increase Eye-Tracking Robustness, Accuracy

Our general approach involves testing and reporting on the impact of several contemporary eye segmentation networks on the

Gaussian Connectivity-Driven EEG Imaging for Deep Learning-Based

The network is trained with a multi-objective loss that jointly optimizes reconstruction fidelity, classification accuracy,

Evaluating the Impact of Backbone Networks and Input

In this study, we investigate the impact of different deep learning backbone architectures and input image resolutions

Eye tracker accuracy and precision

Accuracy and precision are important concepts for understanding and for evaluating the quality of eye tracking data. Accuracy is the

Development and validation of a deep learning model to predict visual

The KongMing Model, developed and tested by a nationwide, multicentre dataset, showed excellent performance in

Enhancing gaze estimation accuracy in wearable eye-tracking devices

Eye-tracking devices are convenient for interpreting human behaviors and intentions, enabling contactless

Channel Characteristic-Based Deep Neural Network Models for Accurate

In this article, for the first time, we propose channel characteristic-based deep neural network (DNN) models for

Review article Backbones-review: Feature extractor networks for deep

For computer vision tasks, features are extracted using different convolutional networks (backbones), while the

arXiv.org e-Print archive

This paper reviews feature extraction networks for deep learning and their applications.

Improving Backbones Performance by Complex Architectures

Using these complex architectures, we transform several backbone networks into complex networks, and proposed

A lightweight deep learning model for automatic segmentation and

Present model is 10 times lighter than Unet (popular for biomedical image segmentation) and have a better segmentation accuracy

Achieving Optimal Speed and Accuracy in Object Detection (YOLOv4)

Achieving Optimal Speed and Accuracy in Object Detection (YOLOv4) In this tutorial, you will learn all about YOLOv4

Principles of operation, accuracy and precision of an Eye Surface

Abstract Purpose: To introduce a newly developed instrument for measuring the topography of the anterior eye,

Multi-class eye disease classification using deep learning

Using a stable dataset of 4,217 High Resolution retina images across the four symptomatic classes, we have

GitHub

Comprehensive evaluations on three RS visual tasks demonstrate DecoupleNet''s superior balance of accuracy and computational

YOLO26 Pose Estimation: Real-Time Keypoint Tutorial

Hands-on YOLO26 pose estimation tutorial: real-time keypoint detection in Python, RLE

Using Deep Learning to Increase Eye-Tracking Robustness,

These measurements have led us to conclude that high-performing eye feature detection neural networks are

Fundus Image-Based Eye Disease Detection Using

This study shows how well EfficientNetB3 distinguishes between various eye disease

LeanStereo: A Leaner Backbone based Stereo Network

This backbone contains two branches: a ''Shallow branch'' respon-sible for capturing the fine details and a ''Deep branch'' that

GitHub

StageMamba achieves 90.03% accuracy, F1 = 0.9015, and MCC = 0.8897 on the augmented dataset — surpassing all CNN

Using deep leaning models to detect ophthalmic diseases: A

Deep learning systems for diabetic retinopathy, age-related macular degeneration, and glaucomatous optic neuropathy

Rethinking Backbone Design for Lightweight 3D Object Detection in

Lightweight backbone design is well-explored for 2D object detection, but research on 3D object detection still remains limited. In this

Devices, Functions, and Applications of Artificial

This review highlights recent advances in optoelectronic synapses for artificial neuromorphic

EyeRAG: graph retrieval-augmented generation for safe and accurate

Large language models promise to transform ophthalmic clinical communication but face challenges from factual

The Ophthalmologist | Increasing AIs Diagnostic Accuracy

A new deep learning model developed by Beijing Jiaotong University may significantly enhance the accuracy and

DeGuNet: Depth-Guided Ultra-Compact Backbones for Efficient

To address these challenges, we propose the Depth-Guided Network (DeGuNet), an ultra-compact, plug-and-play image

Deep Neural Networks for Low-Cost Eye Tracking

Various models of deep neural networks that can be involved in the process of online gaze monitoring are reviewed.

Local eye-net: An attention based deep learning architecture for

We have proposed a deep attention model called LocalEyenet by using Stacked Hourglass (HG) architecture as

Vision-based livestock pose estimation for precision livestock farming

Camera-based pose estimation is becoming a key sensing approach for automated livestock monitoring, yet the selection of camera

HESS

Abstract. The study presents a robust, automated camera gauge for long-term river water level monitoring operating

A Hybrid Deep Learning Framework for Automated Dental Disorder

Our hybrid framework showed remarkable accuracy in detecting dental diseases while using minimal time and resources.

Artificial intelligence support improves diagnosis accuracy in

In this study, we hypothesized that CorneAI assistance can improve efficiency and accuracy of diagnosing anterior

Depth accuracy

Stereo depth accuracy (Z-Accuracy) depends on number of factors that are documented at Improving stereo accuracy. In a nutshell,

[2508.00744] Rethinking Backbone Design for Lightweight 3D Object

Lightweight backbone design is well-explored for 2D object detection, but research on 3D object detection still remains

Cross-dataset late fusion of Camera–LiDAR and radar models

This paper presents a modular late-fusion framework that integrates Camera, LiDAR, and Radar modalities for object

Democratizing eye-tracking? Appearance-based gaze estimation with

We present Residual Appearance-based Gaze Estimation network (RAGE-net), a novel convolutional neural network

Riyamenon09/Eye-disease-Classification-and-Detection-using

This project presents an AI-based pipeline for automated diagnosis of eye diseases from fundus images. The system leverages

DeepRetina: Layer Segmentation of Retina in OCT Images Using

The overall network model of DeepRetina comprises the following operations: extracting and learning the retinal layer characteristics