Semi-Supervised Deep Learning Using Pseudo Labels for Hyperspectral Image Classification

By Hao Wu, Saurabh Prasad. IEEE Transactions on Image Processing, 2018

388 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/bcc122aaebc89a6d6667307c2ac14d405c7acf6c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Danfeng Hong
2. Lorenzo Bruzzone
3. Jocelyn Chanussot
4. Jing Yao
5. Tao Huang
6. Jian Lian
7. Renchao Xie
8. Weiwei Song

In Biomedical Engineering

1. Shutao Li
2. Xudong Kang
3. Leyuan Fang
4. Jon Atli Benediktsson
5. Pedram Ghamisi
6. Daifeng Peng
7. Yongjun Zhang
8. Haiyan Guan

In Media Technology

1. Shutao Li
2. Jon Atli Benediktsson
3. Jocelyn Chanussot
4. Leyuan Fang
5. Pedram Ghamisi
6. Yushi Chen
7. Xudong Kang
8. Danfeng Hong

Citations in the corpus

• Deep Learning for Classification of Hyperspectral Data: A Comparative Review (2019, positive): “A similar approach using RNNs treating hyperspectral pixels as a sequence of reflectances was introduced in [44], including a pseudolabeling scheme for semisupervised learning.”
• Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox (2020, methodology): “For examples, Wu and Prasad attempted to use a clustering model to obtain pseudo labels of unlabeled samples, and then combine the training samples and unlabeled samples (with their pseudo labels) together to train their network [113].”
• Single-Source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification (2022, neutral): “hyperspectral image (HSI) [1], [2], [3].”
• Feature dimensionality reduction: a review (2022, background): “The limited labeled data are applied to fine-tune parameters [167].”
• Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, methodology): “[201] utilized such a model for semi-supervised HSIC by using pseudo labels.”
• Deep Learning for Hyperspectral Image Classification: An Overview (2019, methodology): “Recently, more and more research works [47], [97], [104], [105], [111], [116], [117] focus on designing a robust and effective unsupervised/semisupervised feature learning framework based on deep learning to classify HSIs.”
• A Survey of Machine Learning Techniques Applied to Software Defined Networking (SDN): Research Issues and Challenges (2019, background): “Pseudo Labeling [122], [123] is a simple and efficient semi-supervised learning technique.”
• SemiCDNet: A Semisupervised Convolutional Neural Network for Change Detection in High Resolution Remote-Sensing Images (2020, methodology): “in RS problems, SSL methods have attracted increasing interest toward tasks like classification [41], dimensionality”
• Self Supervised Learning for Few Shot Hyperspectral Image Classification (2022, methodology): “These paradigms have been utilized on hyperspectral data as well [1, 2, 3] showing promising results.”
• A survey: Deep learning for hyperspectral image classification with few labeled samples (2021, background): “In this section, three classical deep learning models, including the autoencoder, convolutional neural network (CNN), and recurrent neural network (RNN), for HSI classification are respectively described, and the relevant references are reviewed.”