Results 61 to 70 of about 2,335 (188)

Empanada MitoNet model files

, 2022
PyTorch jit scripted model files for use in the empanada-dl python package and empanada-napari plugin. MitoNet_v1 is a 55 million parameter Panoptic-DeepLab architecture and MitoNet_v1_mini is a 23 million parameter Panoptic=BiFPN architecture. Quantized
Ryan Conrad, Kedar Narayan
core   +1 more source

EAFE‐OSOD: Efficient Attention Fusion Encoder for Open‐Set Object Detection in UAV Applications

IET Image Processing, Volume 20, Issue 1, January/December 2026.
We propose EAFE‐OSOD, an efficient end‐to‐end framework for open‐set object detection in UAV applications that simultaneously addresses small object detection, computational efficiency, and novel category recognition. The method integrates class‐agnostic mask embedding and CLIP text encoder with streamlined multi‐scale fusion architectures to enable ...
Zicheng Wang, Zhenxiang Pan, Zhiyu Cai, Hui Zhou, Yu Tang, Yingchi Mao   +5 more
wiley   +1 more source

The DCN-BiFPN Object Detection Algorithm based on YOLOv8

Abstract Aiming at the problems of traditional target detection algorithms such as high demand for model equipment, low detection accuracy, high leakage rate of overlapping targets, and repeated detection of the same target, we propose an improved multilayer deformable convolution as well as a method for fusing attention mechanisms, and use ...
Bo Yu, Shun Li, Wei Wang, Yuanze Meng, Dongying Liu   +4 more
openaire   +1 more source

BPS‐YOLO: A Localisation‐Robust Detector for Foreign Objects in Railway Overhead Catenary Systems

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This paper presents BPS‐YOLO, a localisation‐robust detector for foreign object detection in railway overhead catenary systems under complex backgrounds, low illumination, and long‐distance imaging conditions. By integrating C3K2_PLA, attention‐guided bidirectional feature pyramid network (AG‐BiFPN) with GLSA enhancement, and Shape‐IoU as an auxiliary ...
Shichao Quan, Guangnan Zhang, Di Yan, Hongxia Li, Ping Zhang, Yating Liu   +5 more
wiley   +1 more source

YOLOv11–BiFPN–DAAF: An Object Detection Framework for Automated Surface Inspection of Balsa Wood Panels

Automated surface inspection of balsa wood panels is challenging because defects may be small, elongated, weakly contrasted, or visually similar to natural grain patterns.
Washington Chiriboga-Casanova, Efraín Díaz-Macías, Cristian Zambrano-Vega, Edgar Suárez Bardelline, Byron Oviedo   +4 more
core   +1 more source

LAD‐YOLOv8n: A Novel Model for Rare Earth Molten Salt Flame Detection

IET Image Processing, Volume 20, Issue 1, January/December 2026.
This figure illustrates a complete workflow for rare‐earth molten salt flame recognition, including dataset construction and pre‐processing, LAD‐YOLO algorithm design, experimental validation and deployment in the smart detection and automatic system. Specifically, the dataset is collected and established using the orbital mobile robot integrated into ...
Zhiyue Liao, Jiahao Li, Jingchuan Ye, Hao Tang, Xinyu Wu   +4 more
wiley   +1 more source

A BiFPN-SECA Detection Network for Foreign Objects on Top of Railway Freight Vehicles

Signal, Image and Video Processing
Abstract Foreign object detection on top of railway freight vehicles is critical to ensuring the safety and efficiency railway transportation. However, this task faces major challenges such as low accuracy and potential false positives and false negatives.
Sheng Liu, Yiqing Yang, Ting Cao, Yi Zhu
openaire   +2 more sources

DWD‐Net: A Feature Enhancement Network for Detecting Small‐Scale Ships in Synthetic Aperture Radar Imagery

IET Image Processing, Volume 20, Issue 1, January/December 2026.
Synthetic aperture radar (SAR) ship detection remains challenging due to inherent speckle noise, complex sea clutter, variable target scales, and arbitrary ship poses. This paper develops a YOLOv11‐based multi‐scale feature enhancement network, namely DWD‐Net, by integrating deformable convolution v4, a stochastic multi‐scale pooling attention ...
Niu Yameng, Hu Shengliang, Liu Yiping, Wu Hai, Yang Chen   +4 more
wiley   +1 more source

The structure of the BiFPN.

An essential industrial application is the examination of surface flaws in hot-rolled steel strips. While automatic visual inspection tools must meet strict real-time performance criteria for inspecting hot-rolled steel strips, their capabilities are ...
Haoyue Huang (3450605), Qiuyan Wang (237527), Haibing Dong (17846963)   +2 more
core   +1 more source

PAS‐YOLOv13: An Improved Network for Ethnic Costume Image Detection

IET Image Processing, Volume 20, Issue 1, January/December 2026.
PAS‐YOLOv13 is a high‐precision object detection framework designed for ethnic‐clothing images with complex textures and multi‐scale variations. It incorporates a shallow detection branch, ASFF module and a weighted SIoU‐based term to enhance small‐object perception and localization accuracy. Experimental results demonstrate significant improvements in
Huabing Liu, Pengzhi Zhan, Zhicheng Zhan, Fei Liu, Bin Wen   +4 more
wiley   +1 more source