YOLOv5
PulseAugur coverage of YOLOv5 — every cluster mentioning YOLOv5 across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
Low-cost AI system detects fabric defects on edge devices
Researchers have developed a two-stage fabric defect detection system designed for low-cost deployment on edge devices like the NVIDIA Jetson Nano. The system uses a lightweight autoencoder for initial screening, follow…
-
AI models evaluated for African crop detection in new study
A new study published on arXiv evaluates six object detection models for agricultural applications, specifically focusing on plant detection in real-world African farming conditions. The research utilized the AgriAISeg …
-
Drone and Ground Vehicle Navigation System for Snow-Covered Terrain
Researchers have developed a novel navigation framework for drones and ground vehicles operating in challenging, snow-covered terrains. This system utilizes an efficient U-Net architecture for real-time road segmentatio…
-
EigenCAM outperforms Grad-CAM++ for YOLOv5 object detection
The article explains why EigenCAM is a superior choice over Grad-CAM++ for object detection models like YOLOv5. The primary advantage highlighted is EigenCAM's use of principal component analysis (PCA) on feature channe…
-
AI models struggle with rural Chinese roads; synthetic data offers partial solution
Researchers have developed a new dataset and evaluation methodology for object detection in Chinese rural autonomous driving scenarios, addressing data scarcity challenges. The study mixed real-world data from Weishi Co…
-
YOLOv7-Large achieves 90.4% mAP50 for ancient coin character recognition
Researchers have developed a deep learning approach using YOLO variants for character recognition on ancient Roman Republican coins. They created a new dataset of 5,654 coin images with 38,808 annotations for 21 charact…
-
New AdvSerial framework enables physical adversarial attacks on pedestrian detectors
Researchers have developed AdvSerial, a novel framework for creating physical adversarial attacks against pedestrian detection systems used in infrastructure like traffic cameras and smart city surveillance. This method…
-
New research tackles annotation efficiency for object detection models
Two new research papers explore advanced methods for improving object detection annotation efficiency. The first paper introduces a foundation-model-collaborative active learning framework that uses dual-source uncertai…
-
LVLMs show promise for SOTIF-compliant object detection in autonomous vehicles · 2 sources tracked
A new research paper evaluates Large Vision-Language Models (LVLMs) for 2D object detection in automated driving systems, focusing on Safety Of The Intended Functionality (SOTIF) conditions. The study used the PeSOTIF d…
-
AI model automates white blood cell analysis with 99% accuracy
Researchers have developed a novel hybrid machine learning model, LeukocyteCount, to automate the identification and counting of leukocytes (white blood cells) in blood samples. This model integrates Yolov5 for initial …
-
New WIDER-FAIR dataset reveals bias in face detection models
Researchers have introduced WIDER-FAIR, a new dataset designed to evaluate fairness in face detection models. Built upon the WIDER-FACE benchmark, WIDER-FAIR includes manual annotations for perceived ethnicity and sex a…
-
New PNAFusion method enhances multispectral object detection efficiency
Researchers have developed a novel approach called Progressive Pixel-Neighborhood Deformable Cross-Attention (PNAFusion) to improve multispectral object detection. This method addresses the computational cost of global …
-
AI-powered app translates visual data into auditory feedback for the blind
A new AI-Sight app, also known as SoundSight, has been developed to provide auditory feedback for visually impaired individuals using mobile technology. This application leverages AI models like DeepLabV3, YOLOv5, and Y…