IARS Segnet

SegNet, a deep learning architecture for semantic segmentation, is being adapted and extended for various applications requiring precise pixel-level image understanding. Current research focuses on improving SegNet's efficiency and accuracy for real-time processing in diverse domains, including autonomous driving (using 4D LiDAR data), wildfire detection from drone imagery, and medical image analysis (e.g., melanoma segmentation). These advancements leverage techniques like attention mechanisms, residual connections, and efficient feature extraction to enhance both performance and interpretability, thereby increasing the practical impact of SegNet across multiple scientific and engineering fields.

Papers

October 16, 2024

FragNet: A Graph Neural Network for Molecular Property Prediction with Four Layers of Interpretability
Gihan Panapitiya, Peiyuan Gao, C Mark Maupin, Emily G Saldanha
Graph Neural Network Inherent Interpretability Multi Layer Molecular Property Prediction Molecular Property Molecular Structure Molecular Fragment IARS Segnet

June 24, 2024

SegNet4D: Efficient Instance-Aware 4D LiDAR Semantic Segmentation for Driving Scenarios
Neng Wang, Ruibin Guo, Chenghao Shi, Ziyue Wang, Hui Zhang, Huimin Lu, Zhiqiang Zheng, Xieyuanli Chen
Autonomous Driving Lidar Semantic Segmentation IARS Segnet Multi Scan Semantic Segmentation

February 29, 2024

SegNet: A Segmented Deep Learning based Convolutional Neural Network Approach for Drones Wildfire Detection
Aditya V. Jonnalagadda, Hashim A. Hashim
Deep Learning Convolutional Neural Network Wildfire Detection Fire Detection IARS Segnet

October 31, 2023

IARS SegNet: Interpretable Attention Residual Skip connection SegNet for melanoma segmentation
Shankara Narayanan, Sikha OK, Raul Benitez
Convolutional Block Skin Lesion Segmentation Segmentation Framework Melanoma Classification Residual Attention IARS Segnet

July 25, 2023

Image Segmentation Keras : Implementation of Segnet, FCN, UNet, PSPNet and other models in Keras
Divam Gupta
Semantic Segmentation Segmentation Model Pixel Level Computer Vision Task segmentatiOn Challenge IARS Segnet

July 6, 2023

March 20, 2023

Bimodal SegNet: Instance Segmentation Fusing Events and RGB Frames for Robotic Grasping
Sanket Kachole, Xiaoqian Huang, Fariborz Baghaei Naeini, Rajkumar Muthusamy, Dimitrios Makris, Yahya Zweiri
Instance Segmentation Robotic Grasping Event Description Object Segmentation Single RGB Image Better Segmentation Atrous Convolution IARS Segnet

November 21, 2022

SegNeRF: 3D Part Segmentation with Neural Radiance Fields
Jesus Zarzar, Sara Rojas, Silvio Giancola, Bernard Ghanem
Neural Radiance Field Novel View Synthesis Part Segmentation Semantic Space Neural Field Representation IARS Segnet

IARS Segnet

Papers

FragNet: A Graph Neural Network for Molecular Property Prediction with Four Layers of Interpretability

SegNet4D: Efficient Instance-Aware 4D LiDAR Semantic Segmentation for Driving Scenarios

SegNet: A Segmented Deep Learning based Convolutional Neural Network Approach for Drones Wildfire Detection

IARS SegNet: Interpretable Attention Residual Skip connection SegNet for melanoma segmentation

Image Segmentation Keras : Implementation of Segnet, FCN, UNet, PSPNet and other models in Keras

SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks

SeLiNet: Sentiment enriched Lightweight Network for Emotion Recognition in Images

Bimodal SegNet: Instance Segmentation Fusing Events and RGB Frames for Robotic Grasping

SegNeRF: 3D Part Segmentation with Neural Radiance Fields