Localization is all you evaluate: Data leakage in online map** datasets and how to fix it

A Lilja, J Fu, E Stenborg… - Proceedings of the …, 2024 - openaccess.thecvf.com
The task of online map** is to predict a local map using current sensor observations eg
from lidar and camera without relying on a pre-built map. State-of-the-art methods are based …

Hyperspectral image classification using an encoder-decoder model with depthwise separable convolution, squeeze and excitation blocks

XT Nguyen, GS Tran - Earth Science Informatics, 2024 - Springer
Remote sensing is one of the major domains witnessing the increasingly significant interest
in Hyperspectral image (HSI) classification. One recent approach achieving great success in …

Hyperspectral Image Classification Framework Based on Multichannel Graph Convolutional Networks and Class-Guided Attention Mechanism

H Feng, Y Wang, C Chen, D Xu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Graph convolutional networks (GCNs) can extract features of samples in non-Euclidean
space, which can be used for hyperspectral image (HSI) classification in collaboration with …

Hyperspectral Image Classification Based on Double-Branch Multi-Scale Dual-Attention Network

H Zhang, H Liu, R Yang, W Wang, Q Luo, C Tu - Remote Sensing, 2024 - mdpi.com
Although extensive research shows that CNNs achieve good classification results in HSI
classification, they still struggle to effectively extract spectral sequence information from …

Constrained Spectral–Spatial Attention Residual Network and New Cross-Scene Dataset for Hyperspectral Classification

S Li, B Chen, N Wang, Y Shi, G Zhang, J Liu - Electronics, 2024 - mdpi.com
Hyperspectral image classification is widely applied in several fields. Since existing datasets
focus on a single scene, current deep learning-based methods typically divide patches …

AMBER--Advanced SegFormer for Multi-Band Image Segmentation: an application to Hyperspectral Imaging

A Dosi, M Brescia, S Cavuoti, M D'Aniello… - arxiv preprint arxiv …, 2024 - arxiv.org
Deep learning has revolutionized the field of hyperspectral image (HSI) analysis, enabling
the extraction of complex and hierarchical features. While convolutional neural networks …

Enhancing Hyper-Spectral Image Classification with Reinforcement Learning and Advanced Multi-Objective Binary Grey Wolf Optimization.

M Shoeibi, MMS Nevisi, R Salehi… - Computers …, 2024 - search.ebscohost.com
Hyperspectral (HS) image classification plays a crucial role in numerous areas including
remote sensing (RS), agriculture, and the monitoring of the environment. Optimal band …

Analyzing Information Leakage on Video Object Detection Datasets by Splitting Images Into Clusters With High Spatiotemporal Correlation

RBD Figueiredo, HA Mendes - IEEE Access, 2024 - ieeexplore.ieee.org
Random splitting strategy is a common approach for training, testing, and validating object
detection algorithms based on deep learning. Is common for datasets to have images …