Hyperspectral Image Classification using Uncertainty and Diversity based Active Learning

There has been extensive research in the field of Hyperspectral Image Classification using deep neural networks. The deep learning based approaches requires huge amount of labelled data samples. But in the case of Hyperspectral Image, there are less number of labelled data samples. Therefore, we can adopt Active Learning combined with deep learning based approaches to be able to extract most informative data samples. By using this technique, we can train the classifier to achieve better classification accuracies with less number of labelled data samples. There is considerable amount of research carried out for selecting diverse data samples from the pool of unlabeled data samples. We present a novel diversity-based Active Learning approach utilizing the information of clustered data distribution. We incorporate diversity criteria with Active Learning selection criteria and combine it with Convolutional Neural Network for feature extraction and classification. This approach helps us in obtaining most informative and diverse data samples. We have compared our proposed approach with three other sampling methods in terms of classification accuracies, Cohen Kappa score, which shows that our approach gives better results with comparison to other sampling methods.

Download Full-text

Active Learning Plus Deep Learning Can Establish Cost-Effective and Robust Model for Multichannel Image: A Case on Hyperspectral Image Classification

Sensors ◽

10.3390/s20174975 ◽

2020 ◽

Vol 20 (17) ◽

pp. 4975

Author(s):

Fangyu Shi ◽

Zhaodi Wang ◽

Menghan Hu ◽

Guangtao Zhai

Keyword(s):

Deep Learning ◽

Active Learning ◽

Image Classification ◽

Large Scale ◽

Hyperspectral Image ◽

Image Annotation ◽

Learning Algorithm ◽

Magnetic Resonance Images ◽

Biological Engineering ◽

Hyperspectral Image Classification

Relying on large scale labeled datasets, deep learning has achieved good performance in image classification tasks. In agricultural and biological engineering, image annotation is time-consuming and expensive. It also requires annotators to have technical skills in specific areas. Obtaining the ground truth is difficult because natural images are expensive. In addition, images in these areas are usually stored as multichannel images, such as computed tomography (CT) images, magnetic resonance images (MRI), and hyperspectral images (HSI). In this paper, we present a framework using active learning and deep learning for multichannel image classification. We use three active learning algorithms, including least confidence, margin sampling, and entropy, as the selection criteria. Based on this framework, we further introduce an “image pool” to make full advantage of images generated by data augmentation. To prove the availability of the proposed framework, we present a case study on agricultural hyperspectral image classification. The results show that the proposed framework achieves better performance compared with the deep learning model. Manual annotation of all the training sets achieves an encouraging accuracy. In comparison, using active learning algorithm of entropy and image pool achieves a similar accuracy with only part of the whole training set manually annotated. In practical application, the proposed framework can remarkably reduce labeling effort during the model development and upadting processes, and can be applied to multichannel image classification in agricultural and biological engineering.

Download Full-text

Hyperspectral Image Classification with Feature-Oriented Adversarial Active Learning

Remote Sensing ◽

10.3390/rs12233879 ◽

2020 ◽

Vol 12 (23) ◽

pp. 3879

Author(s):

Guangxing Wang ◽

Peng Ren

Keyword(s):

Deep Learning ◽

Active Learning ◽

Image Classification ◽

Hyperspectral Image ◽

Hyperspectral Images ◽

Hyperspectral Image Classification ◽

The Real ◽

Learning Classifier ◽

Feature Variability ◽

High Level

Deep learning classifiers exhibit remarkable performance for hyperspectral image classification given sufficient labeled samples but show deficiency in the situation of learning with limited labeled samples. Active learning endows deep learning classifiers with the ability to alleviate this deficiency. However, existing active deep learning methods tend to underestimate the feature variability of hyperspectral images when querying informative unlabeled samples subject to certain acquisition heuristics. A major reason for this bias is that the acquisition heuristics are normally derived based on the output of a deep learning classifier, in which representational power is bounded by the number of labeled training samples at hand. To address this limitation, we developed a feature-oriented adversarial active learning (FAAL) strategy, which exploits the high-level features from one intermediate layer of a deep learning classifier for establishing an acquisition heuristic based on a generative adversarial network (GAN). Specifically, we developed a feature generator for generating fake high-level features and a feature discriminator for discriminating between the real high-level features and the fake ones. Trained with both the real and the fake high-level features, the feature discriminator comprehensively captures the feature variability of hyperspectral images and yields a powerful and generalized discriminative capability. We leverage the well-trained feature discriminator as the acquisition heuristic to measure the informativeness of unlabeled samples. Experimental results validate the effectiveness of both (i) the full FAAL framework and (ii) the adversarially learned acquisition heuristic, for the task of classifying hyperspectral images with limited labeled samples.

Download Full-text

Hyperspectral image classification based on active learning

Journal of Computer Applications ◽

10.3724/sp.j.1087.2013.03441 ◽

2013 ◽

Vol 33 (12) ◽

pp. 3441-3443

Author(s):

Zedong HAO ◽

Songsong YU ◽

Jihong GUAN

Keyword(s):

Active Learning ◽

Image Classification ◽

Hyperspectral Image ◽

Hyperspectral Image Classification

Download Full-text

Evaluating the Performance of the state-of-the-art HybridSN Deep Learning Algorithm for Airborne Hyperspectral Image Classification

IOP Conference Series Earth and Environmental Science ◽

10.1088/1755-1315/767/1/012019 ◽

2021 ◽

Vol 767 (1) ◽

pp. 012019

Author(s):

M A A M Abidin ◽

H Z M Shafri ◽

M M A Al-Habshi ◽

N S N Shaharum

Keyword(s):

Deep Learning ◽

Image Classification ◽

Hyperspectral Image ◽

Learning Algorithm ◽

State Of The Art ◽

The State ◽

Hyperspectral Image Classification ◽

Deep Learning Algorithm

Download Full-text

Hyperspectral Image Classification Based on Multi-Scale Residual Network with Attention Mechanism

Remote Sensing ◽

10.3390/rs13030335 ◽

2021 ◽

Vol 13 (3) ◽

pp. 335

Author(s):

Yuhao Qing ◽

Wenyi Liu

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Image Classification ◽

Classification Accuracy ◽

Hyperspectral Image ◽

Principal Component ◽

Hyperspectral Image Classification ◽

Deep Network ◽

Multi Scale

In recent years, image classification on hyperspectral imagery utilizing deep learning algorithms has attained good results. Thus, spurred by that finding and to further improve the deep learning classification accuracy, we propose a multi-scale residual convolutional neural network model fused with an efficient channel attention network (MRA-NET) that is appropriate for hyperspectral image classification. The suggested technique comprises a multi-staged architecture, where initially the spectral information of the hyperspectral image is reduced into a two-dimensional tensor, utilizing a principal component analysis (PCA) scheme. Then, the constructed low-dimensional image is input to our proposed ECA-NET deep network, which exploits the advantages of its core components, i.e., multi-scale residual structure and attention mechanisms. We evaluate the performance of the proposed MRA-NET on three public available hyperspectral datasets and demonstrate that, overall, the classification accuracy of our method is 99.82 %, 99.81%, and 99.37, respectively, which is higher compared to the corresponding accuracy of current networks such as 3D convolutional neural network (CNN), three-dimensional residual convolution structure (RES-3D-CNN), and space–spectrum joint deep network (SSRN).

Download Full-text