A Double-Strategy-Check Active Learning Algorithm for Hyperspectral Image Classification

2019 ◽  
Vol 85 (11) ◽  
pp. 841-851
Author(s):  
Ying Cui ◽  
Xiaowei Ji ◽  
Kai Xu ◽  
Liguo Wang
Keyword(s):  
Active Learning ◽  
Image Classification ◽  
Traditional Method ◽  
Hyperspectral Image ◽  
Learning Algorithm ◽  
Semisupervised Learning ◽  
Hyperspectral Data ◽  
Data Sets ◽  
Classification Methods ◽  
Hyperspectral Image Classification

Applying limited labeled samples to improve classification results is a challenge in hyperspectral images. Active Learning (AL) and Semisupervised Learning (SSL) are two promising techniques to achieve this challenge. Combining AL with SSL is an excellent idea for hyperspectral image classification. The traditional method, such as the Collaborative Active and Semisupervised Learning algorithm (CASSL), may introduce many incorrect pseudolabels and shows premature convergence. To overcome these drawbacks, a novel framework named Double-Strategy-Check Collaborative Active and Semisupervised Learning (DSC-CASSL) is proposed in this paper. This framework combines two different AL algorithms and SSL in a collaborative mode. The double-strategy verification can gradually improve the pseudolabeling accuracy and facilitate SSL. We evaluate the performance of DSC-CASSL on four hyperspectral data sets and compare it with that of four hyperspectral image classification methods. Our results suggest that DSC-CASSL leads to consistent improvement for hyperspectral image classification.

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

Sensors ◽  
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.

Active Learning via Multi-View and Local Proximity Co-Regularization for Hyperspectral Image Classification

2011 ◽  
Vol 5 (3) ◽  
pp. 618-628 ◽  
Author(s):  
Wei Di ◽  
Melba M. Crawford
Keyword(s):  
Active Learning ◽  
Image Classification ◽  
Hyperspectral Image ◽  
Computational Cost ◽  
Hyperspectral Data ◽  
Unlabeled Data ◽  
Support Vector ◽  
Svm Classifier ◽  
Small Subset ◽  
Hyperspectral Image Classification

A novel co-regularization framework for active learning is proposed for hyperspectral image classification. The first regularizer explores the intrinsic multi-view information embedded in the hyperspectral data. By adaptively and quantitatively measuring the disagreement level, it focuses only on samples with high uncertainty and builds a contention pool which is a small subset of the overall unlabeled data pool, thereby mitigating the computational cost. The second regularizer is based on the “consistency assumption” and designed on a spatial or the spectral based manifold space. It serves to further focus on the most informative samples within the contention pool by penalizing rapid changes in the classification function evaluated on proximally close samples in a local region. Such changes may be due to the lack of capability of the current learner to describe the unlabeled data. Incorporating manifold learning into the active learning process enforces the clustering assumption and avoids the degradation of the distance measure associated with the original high-dimensional spectral features. One spatial and two local spectral embedding methods are considered in this study, in conjunction with the support vector machine (SVM) classifier implemented with a radial basis function (RBF) kernel. Experiments show excellent performance on AVIRIS and Hyperion hyperspectral data as compared to random sampling and the state-of-the-art SVMSIMPLE.

Semi-Supervised Classification for Hyperspectral Image Based on Tri-Training

2014 ◽  
Vol 687-691 ◽  
pp. 3644-3647 ◽  
Author(s):  
Li Guo Wang ◽  
Yue Shuang Yang ◽  
Ting Ting Lu
Keyword(s):  
Supervised Classification ◽  
Hyperspectral Image ◽  
Learning Algorithm ◽  
Hyperspectral Data ◽  
Data Sets ◽  
Hyperspectral Image Classification ◽  
Training Set ◽  
De Algorithm ◽  
Training Samples ◽  
Limited Training Samples

Hyperspectral image classification is difficult due to the high dimensional features but limited training samples. Tri-training learning is a widely used semi-supervised classification method that addresses the problem of lacking of labeled examples. In this paper, a novel semi-supervised learning algorithm based on tri-training method is proposed. The proposed algorithm combines margin sampling (MS) technique and differential evolution (DE) algorithm to select the most informative samples and perturb them randomly. Then the samples we obtained, which can fulfill the labeled data distribution and introduce diversity to multiple classifiers, are added to training set to train base classifiers for tri-training. The proposed algorithm is experimentally validated using real hyperspectral data sets, indicating that the combination of MS and DE can significantly reduce the need of labeled samples while achieving high accuracy compared with state-of-the-art algorithms.

scholarly journals Multipath Residual Network for Spectral-Spatial Hyperspectral Image Classification

2019 ◽  
Vol 11 (16) ◽  
pp. 1896 ◽  
Author(s):  
Zhe Meng ◽  
Lingling Li ◽  
Xu Tang ◽  
Zhixi Feng ◽  
Licheng Jiao ◽  
...  
Keyword(s):  
Hyperspectral Image ◽  
State Of The Art ◽  
Gradient Flow ◽  
Hyperspectral Data ◽  
Data Sets ◽  
Classification Models ◽  
Classification Methods ◽  
Hyperspectral Image Classification ◽  
Residual Network ◽  
Residual Functions

Convolutional neural networks (CNNs) have recently shown outstanding capability for hyperspectral image (HSI) classification. In this work, a novel CNN model is proposed, which is wider than other existing deep learning-based HSI classification models. Based on the fact that very deep residual networks (ResNets) behave like an ensemble of relatively shallow networks, our proposed network, called multipath ResNet (MPRN), employs multiple residual functions in the residual blocks to make the network wider, rather than deeper. The proposed network consists of shorter-medium paths for efficient gradient flow and replaces the stacking of multiple residual blocks in ResNet with fewer residual blocks but more parallel residual functions in each of it. Experimental results on three real hyperspectral data sets demonstrate the superiority of the proposed method over several state-of-the-art classification methods.

scholarly journals GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION

2017 ◽  
Vol XLII-4/W4 ◽  
pp. 91-96
Author(s):  
N. Jamshidpour ◽  
S. Homayouni ◽  
A. Safari
Keyword(s):  
Image Classification ◽  
Supervised Classification ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Main Idea ◽  
Hyperspectral Data ◽  
Training Data ◽  
Data Sets ◽  
Hyperspectral Image Classification ◽  
Data Set

Hyperspectral image classification has been one of the most popular research areas in the remote sensing community in the past decades. However, there are still some problems that need specific attentions. For example, the lack of enough labeled samples and the high dimensionality problem are two most important issues which degrade the performance of supervised classification dramatically. The main idea of semi-supervised learning is to overcome these issues by the contribution of unlabeled samples, which are available in an enormous amount. In this paper, we propose a graph-based semi-supervised classification method, which uses both spectral and spatial information for hyperspectral image classification. More specifically, two graphs were designed and constructed in order to exploit the relationship among pixels in spectral and spatial spaces respectively. Then, the Laplacians of both graphs were merged to form a weighted joint graph. The experiments were carried out on two different benchmark hyperspectral data sets. The proposed method performed significantly better than the well-known supervised classification methods, such as SVM. The assessments consisted of both accuracy and homogeneity analyses of the produced classification maps. The proposed spectral-spatial SSL method considerably increased the classification accuracy when the labeled training data set is too scarce.When there were only five labeled samples for each class, the performance improved 5.92% and 10.76% compared to spatial graph-based SSL, for AVIRIS Indian Pine and Pavia University data sets respectively.

A novel semi-supervised learning framework for hyperspectral image classification

2016 ◽  
Vol 14 (02) ◽  
pp. 1640005 ◽  
Author(s):  
Zhijing Ye ◽  
Hong Li ◽  
Yalong Song ◽  
Jianzhong Wang ◽  
Jon Atli Benediktsson
Keyword(s):  
Image Classification ◽  
Supervised Learning ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Hyperspectral Data ◽  
Data Sets ◽  
Hyperspectral Image Classification ◽  
Learning Framework ◽  
Classification Framework ◽  
Adaptive Interpolation

In this paper, we propose a novel semi-supervised learning classification framework using box-based smooth ordering and multiple 1D-embedding-based interpolation (M1DEI) in [J. Wang, Semi-supervised learning using multiple one-dimensional embedding-based adaptive interpolation, Int. J. Wavelets Multiresolut. Inf. Process. 14(2) (2016) 11 pp.] for hyperspectral images. Due to the lack of labeled samples, conventional supervised approaches cannot generally perform efficient enough. On the other hand, obtaining labeled samples for hyperspectral image classification is difficult, expensive and time-consuming, while unlabeled samples are easily available. The proposed method can effectively overcome the lack of labeled samples by introducing new labeled samples from unlabeled samples in a label boosting framework. Furthermore, the proposed method uses spatial information from the pixels in the neighborhood of the current pixel to better catch the features of hyperspectral image. The proposed idea is that, first, we extract the box (cube data) of each pixel from its neighborhood, then apply multiple 1D interpolation to construct the classifier. Experimental results on three hyperspectral data sets demonstrate that the proposed method is efficient, and outperforms recent popular semi-supervised methods in terms of accuracies.

Sign in / Sign up

Export Citation Format

Share Document