A Hyperspectral Image Classification Method Based on Multi-Discriminator Generative Adversarial Networks

Small Sample Hyperspectral Image Classification Based on the Random Patches Network and Recursive Filtering

In recent years, different deep learning frameworks were introduced for hyperspectral image (HSI) classification. However, the proposed network models have a higher model complexity, and do not provide high classification accuracy if few-shot learning is used. This paper presents an HSI classification method that combines random patches network (RPNet) and recursive filtering (RF) to obtain informative deep features. The proposed method first convolves image bands with random patches to extract multi-level deep RPNet features. Thereafter, the RPNet feature set is subjected to dimension reduction through principal component analysis (PCA), and the extracted components are filtered using the RF procedure. Finally, the HSI spectral features and the obtained RPNet-RF features are combined to classify the HSI using a support vector machine (SVM) classifier. In order to test the performance of the proposed RPNet-RF method, some experiments were performed on three widely known datasets using a few training samples for each class, and classification results were compared with those obtained by other advanced HSI classification methods adopted for small training samples. The comparison showed that the RPNet-RF classification is characterized by higher values of such evaluation metrics as overall accuracy and Kappa coefficient.

Revisiting Consistency for Semi-Supervised Semantic Segmentation

Semi-supervised learning is an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires substantial effort. This paper considers semi-supervised algorithms that enforce consistent predictions over perturbed unlabeled inputs. We study the advantages of perturbing only one of the two model instances and preventing the backward pass through the unperturbed instance. We also propose a competitive perturbation model as a composition of geometric warp and photometric jittering. We experiment with efficient models due to their importance for real-time and low-power applications. Our experiments show clear advantages of (1) one-way consistency, (2) perturbing only the student branch, and (3) strong photometric and geometric perturbations. Our perturbation model outperforms recent work and most of the contribution comes from the photometric component. Experiments with additional data from the large coarsely annotated subset of Cityscapes suggest that semi-supervised training can outperform supervised training with coarse labels. Our source code is available at https://github.com/Ivan1248/semisup-seg-efficient.

Enhancing classification of cells procured from bone marrow aspirate smears using generative adversarial networks and sequential convolutional neural network

BACKGROUND AND OBJECTIVE

Leukemia represents 30% of all pediatric cancers and is considered the most common malignancy affecting adults and children. Cell differential count obtained from bone marrow aspirate smears is crucial for diagnosing hematologic diseases. Classification of these cell types is an essential task towards analyzing the disease, but it is time-consuming and requires intensive manual intervention. While machine learning has shown excellent outcomes in automating medical diagnosis, it needs ample data to build an efficient model for real-world tasks. This paper aims to generate synthetic data to enhance the classification accuracy of cells obtained from bone marrow aspirate smears.

METHODS

A three-stage architecture has been proposed. We first collaborate with experts from the medical domain to prepare a dataset that consolidates microscopic cell images obtained from bone marrow aspirate smears from three different sources. The second stage involves a generative adversarial networks (GAN) model to generate synthetic microscopic cell images. We propose a GAN model consisting of three networks; generator discriminator and classifier. We train the GAN model with the loss function of Wasserstein GAN with gradient penalty (WGAN-GP). Since our GAN has an additional classifier and was trained using WGAN-GP, we named our model C-WGAN-GP. In the third stage, we propose a sequential convolutional neural network (CNN) to classify cells in the original and synthetic dataset to demonstrate how generating synthetic data and utilizing a simple sequential CNN model can enhance the accuracy of cell classification.

RESULTS

We validated the proposed C-WGAN-GP and sequential CNN model with various evaluation metrics and achieved a classification accuracy of 96.98% using the synthetic dataset. We have presented each cell type's accuracy, specificity, and sensitivity results. The sequential CNN model achieves the highest accuracy for neutrophils with an accuracy rate of 97.5%. The highest value for sensitivity and specificity are 97.1% and 97%. Our proposed GAN model achieved an inception score of 14.52 ± 0.10, significantly better than the existing GAN models.

CONCLUSIONS

Using three network GAN architecture produced more realistic synthetic data than existing models. Sequential CNN model with the synthetic data achieved higher classification accuracy than the original data.

Individual Tree Species Classification Based on Convolutional Neural Networks and Multitemporal High-Resolution Remote Sensing Images

The classification of individual tree species (ITS) is beneficial to forest management and protection. Previous studies in ITS classification that are primarily based on airborne LiDAR and aerial photographs have achieved the highest classification accuracies. However, because of the complex and high cost of data acquisition, it is difficult to apply ITS classification in the classification of large-area forests. High-resolution, satellite remote sensing data have abundant sources and significant application potential in ITS classification. Based on Worldview-3 and Google Earth images, convolutional neural network (CNN) models were employed to improve the classification accuracy of ITS by fully utilizing the feature information contained in different seasonal images. Among the three CNN models, DenseNet yielded better performances than ResNet and GoogLeNet. It offered an OA of 75.1% for seven tree species using only the WorldView-3 image and an OA of 78.1% using the combinations of WorldView-3 and autumn Google Earth images. The results indicated that Google Earth images with suitable temporal detail could be employed as auxiliary data to improve the classification accuracy.

Hyperspectral image spectral-spatial classification via weighted Laplacian smoothing constraint-based sparse representation

As a powerful tool in hyperspectral image (HSI) classification, sparse representation has gained much attention in recent years owing to its detailed representation of features. In particular, the results of the joint use of spatial and spectral information has been widely applied to HSI classification. However, dealing with the spatial relationship between pixels is a nontrivial task. This paper proposes a new spatial-spectral combined classification method that considers the boundaries of adjacent features in the HSI. Based on the proposed method, a smoothing-constraint Laplacian vector is constructed, which consists of the interest pixel and its four nearest neighbors through their weighting factor. Then, a novel large-block sparse dictionary is developed for simultaneous orthogonal matching pursuit. Our proposed method can obtain a better accuracy of HSI classification on three real HSI datasets than the existing spectral-spatial HSI classifiers. Finally, the experimental results are presented to verify the effectiveness and superiority of the proposed method.

Adaptive Weighting Feature Fusion Approach Based on Generative Adversarial Network for Hyperspectral Image Classification

Recently, generative adversarial network (GAN)-based methods for hyperspectral image (HSI) classification have attracted research attention due to their ability to alleviate the challenges brought by having limited labeled samples. However, several studies have demonstrated that existing GAN-based HSI classification methods are limited in redundant spectral knowledge and cannot extract discriminative characteristics, thus affecting classification performance. In addition, GAN-based methods always suffer from the model collapse, which seriously hinders their development. In this study, we proposed a semi-supervised adaptive weighting feature fusion generative adversarial network (AWF2-GAN) to alleviate these problems. We introduced unlabeled data to address the issue of having a small number of samples. First, to build valid spectral–spatial feature engineering, the discriminator learns both the dense global spectrum and neighboring separable spatial context via well-designed extractors. Second, a lightweight adaptive feature weighting component is proposed for feature fusion; it considers four predictive fusion options, that is, adding or concatenating feature maps with similar or adaptive weights. Finally, for the mode collapse, the proposed AWF2-GAN combines supervised central loss and unsupervised mean minimization loss for optimization. Quantitative results on two HSI datasets show that our AWF2-GAN achieves superior performance over state-of-the-art GAN-based methods.

A Hyperspectral Image Classification Approach Based on Feature Fusion and Multi-Layered Gradient Boosting Decision Trees

At present, many Deep Neural Network (DNN) methods have been widely used for hyperspectral image classification. Promising classification results have been obtained by utilizing such models. However, due to the complexity and depth of the model, increasing the number of model parameters may lead to an overfitting of the model, especially when training data are insufficient. As the performance of the model mainly depends on sufficient data and a large network with reasonably optimized hyperparameters, using DNNs for classification requires better hardware conditions and sufficient training time. This paper proposes a feature fusion and multi-layered gradient boosting decision tree model (FF-DT) for hyperspectral image classification. First, we fuse extended morphology profiles (EMPs), linear multi-scale spatial characteristics, and nonlinear multi-scale spatial characteristics as final features to extract both special and spectral features. Furthermore, a multi-layered gradient boosting decision tree model is constructed for classification. We conduct experiments based on three datasets, which in this paper are referred to as the Pavia University, Indiana Pines, and Salinas datasets. It is shown that the proposed FF-DT achieves better performance in classification accuracy, training conditions, and time consumption than other current classical hyperspectral image classification methods.

Generative Adversarial Networks Based on Collaborative Learning and Attention Mechanism for Hyperspectral Image Classification

Classifying hyperspectral images (HSIs) with limited samples is a challenging issue. The generative adversarial network (GAN) is a promising technique to mitigate the small sample size problem. GAN can generate samples by the competition between a generator and a discriminator. However, it is difficult to generate high-quality samples for HSIs with complex spatial–spectral distribution, which may further degrade the performance of the discriminator. To address this problem, a symmetric convolutional GAN based on collaborative learning and attention mechanism (CA-GAN) is proposed. In CA-GAN, the generator and the discriminator not only compete but also collaborate. The shallow to deep features of real multiclass samples in the discriminator assist the sample generation in the generator. In the generator, a joint spatial–spectral hard attention module is devised by defining a dynamic activation function based on a multi-branch convolutional network. It impels the distribution of generated samples to approximate the distribution of real HSIs both in spectral and spatial dimensions, and it discards misleading and confounding information. In the discriminator, a convolutional LSTM layer is merged to extract spatial contextual features and capture long-term spectral dependencies simultaneously. Finally, the classification performance of the discriminator is improved by enforcing competitive and collaborative learning between the discriminator and generator. Experiments on HSI datasets show that CA-GAN obtains satisfactory classification results compared with advanced methods, especially when the number of training samples is limited.