Land use and land cover classification with hyperspectral data: A comprehensive review of methods, challenges and future directions

MA Moharram, DM Sundaram - Neurocomputing, 2023 - Elsevier
Recently, many efforts have been concentrated on land use land cover (LULC) classification
due to rapid urbanization, environmental pollution, agriculture drought, frequent floods, and …

Towards label-efficient automatic diagnosis and analysis: a comprehensive survey of advanced deep learning-based weakly-supervised, semi-supervised and self …

L Qu, S Liu, X Liu, M Wang, Z Song - Physics in Medicine & …, 2022 - iopscience.iop.org
Histopathological images contain abundant phenotypic information and pathological
patterns, which are the gold standards for disease diagnosis and essential for the prediction …

Neural image compression for gigapixel histopathology image analysis

D Tellez, G Litjens, J Van der Laak… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
We propose Neural Image Compression (NIC), a two-step method to build convolutional
neural networks for gigapixel image analysis solely using weak image-level labels. First …

VIF-Net: An unsupervised framework for infrared and visible image fusion

R Hou, D Zhou, R Nie, D Liu, L Xiong… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Visible images provide abundant texture details and environmental information, while
infrared images benefit from night-time visibility and suppression of highly dynamic regions; …

Visual object tracking by hierarchical attention siamese network

J Shen, X Tang, X Dong, L Shao - IEEE transactions on …, 2019 - ieeexplore.ieee.org
Visual tracking addresses the problem of localizing an arbitrary target in video according to
the annotated bounding box. In this article, we present a novel tracking method by …

Convolutional neural network-based finger-vein recognition using NIR image sensors

HG Hong, MB Lee, KR Park - Sensors, 2017 - mdpi.com
Conventional finger-vein recognition systems perform recognition based on the finger-vein
lines extracted from the input images or image enhancement, and texture feature extraction …

[PDF][PDF] 元学习研究综述

李凡长, 刘洋, 吴鹏翔, 董方, 蔡奇, 王哲 - 计算机学报, 2021 - 159.226.43.17
1)(苏州大学计算机科学与技术学院, 苏州, 215006) 摘要深度学习在大量领域取得优异成果,
但仍然存在着鲁棒性和泛化性较差, 难以学习和适应未观测任务, 极其依赖大规模数据等问题 …

Travelgan: Image-to-image translation by transformation vector learning

M Amodio, S Krishnaswamy - … of the ieee/cvf conference on …, 2019 - openaccess.thecvf.com
Interest in image-to-image translation has grown substantially in recent years with the
success of unsupervised models based on the cycle-consistency assumption. The …

Finger-vein recognition based on deep DenseNet using composite image

JM Song, W Kim, KR Park - Ieee Access, 2019 - ieeexplore.ieee.org
Finger-vein recognition has the advantages of high immutability, as finger veins are located
under the skin, high user convenience, as a non-invasive and contactless capture device, is …

Steel surface defect detection based on self-supervised contrastive representation learning with matching metric

X Hu, J Yang, F Jiang, A Hussain, K Dashtipour… - Applied Soft …, 2023 - Elsevier
Defect detection is crucial in the quality control of industrial applications. Existing supervised
methods are heavily reliant on the large amounts of labeled data. However, labeled data in …