Hyperspectral Image Classification Using CapsNet With Well-Initialized Shallow Layers

Yin, Jingwei; Li, Sen; Zhu, Hongmei; Luo, Xiaoyan

doi:10.1109/lgrs.2019.2891076

Cited by 51 publications

(29 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to verify the effectiveness of the proposed model in the small samples classification of HSI, we compare the experimental results with SVM, two classical deep learning methods 3D-CNN [51] and iCapsNet [23], two advanced semi-supervised deep learning methods HSGAN [31] and CNN+GCN [33], and two meta-learning-based methods RN-FSC [42] and DFSL+SVM [40]. SVM, more suitable for processing the high dimensional data than other traditional classifiers, has been widely used in HSI classification.…”

Section: Comparison and Analysismentioning

confidence: 99%

“…In [22], Li et al proposed a multiscale deep middle-level feature fusion network which can fully fuse the strong complementary and related information among different scale features for HSI classification. In addition, CNN is also combined with Capsule Network (CN) [23], Siamese Network (SN) [24] and other novel network structures, obtaining satisfactory results with sufficient labeled samples.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Induction Network for Small Samples Classification of Hyperspectral Images

Gao

Guo

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Recently, the deep learning models have achieved great success in hyperspectral images classification. However, most of the deep learning models fail to obtain satisfactory results under the condition of small samples due to the contradiction between the large parameter space of the deep learning models and the insufficient labeled samples in hyperspectral images. To address the problem, a deep model based on the induction network is designed in this paper to improve the classification performance of hyperspectral images under the condition of small samples. Specifically, the typical meta-training strategy is adopted, enabling the model to acquire stronger generalization ability, so as to accurately distinguish the new classes with only a few labeled samples (e.g., 5 samples per class). Moreover, in order to deal with the disturbance caused by the various characteristics of the samples in the same class in HSI, the classwise induction module is introduced utilizing the dynamic routing algorithm, which can induce the sample-wise representations to the class-wise level representations. The obtained class-wise level representations possess better separability, allowing the designed model to generate more accurate and robust classification results. Extensive experiments are carried out on three public hyperspectral images to verify the effectiveness of the proposed method. The results demonstrate that our method outperforms existing deep learning methods under the condition of small samples.

show abstract

Section: Comparison and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Induction Network for Small Samples Classification of Hyperspectral Images

Gao

Guo

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Wang et al [20] expand classification frameworks for HSI based on CapsNet, which introduces the affine transformation matrix. Yin et al [21] tune a new CapsNet architecture with three convolutional layers and achieve superior performance in HSI classification to the CNN-based methods. Wang et al [22] resolve the problem that high resolution may increase intraclass difference and interclass similarity with Caps-TripleGAN.…”

Section: Background Formulation a Capsnetsmentioning

confidence: 99%

Hyperspectral Image Classification With CapsNet and Markov Random Fields

et al. 2020

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification is one of the most challenging problems in understanding HSI. Convolutional neural network(CNN), with the strong ability to extract features using the hidden layers in the network, has been introduced to solve this problem. However, several fully connected layers are always appended at the end of CNN, which dramatically reduced the efficiency of space utilization and make the classification algorithm hard to converge. Recently, a new network architecture called capsule network (CapsNet) was presented to improve the CNN. It uses groups of neurons as capsules to replace the neurons in traditional neural networks. Since the capsule can provide superior spectral features and spatial information extracted, its performance is better than the most advanced CNN in some fields. Motivated by this idea, a new remote sensing hyperspectral image classification algorithm called Conv-Caps is proposed to make full use of the advantages of both. We integrate spectral and spatial information into the proposed framework and combine Conv-Caps with Markov Random Field (MRF), which uses the graph cut expansion method to solve the classification task. The Caps-MRF method is further proposed. First, select an initial feature extractor,which a CNN without fully connected layers. Then, the initial recognition feature map is put into the newly designed CapsNet to obtain the probability map. Finally, the MRF model is used to calculate the subdivision labels. The presented method is trained with three real HSI datasets and is compared with the latest methods. We find the framework can produce competitive classification performance.

show abstract

“…The extraction and utilization of spatial features can effectively improve classification accuracy. However, due to the separation of feature extraction process and classification in traditional classification mode, the adaptability between them cannot be fully considered [15]. In addition, the classification results of traditional methods largely depend on the accumulated experience and parameter setting, which lacks stability and robustness.…”

Section: Introductionmentioning

confidence: 99%

Deep Relation Network for Hyperspectral Image Few-Shot Classification

et al. 2020

View full text Add to dashboard Cite

Deep learning has achieved great success in hyperspectral image classification. However, when processing new hyperspectral images, the existing deep learning models must be retrained from scratch with sufficient samples, which is inefficient and undesirable in practical tasks. This paper aims to explore how to accurately classify new hyperspectral images with only a few labeled samples, i.e., the hyperspectral images few-shot classification. Specifically, we design a new deep classification model based on relational network and train it with the idea of meta-learning. Firstly, the feature learning module and the relation learning module of the model can make full use of the spatial–spectral information in hyperspectral images and carry out relation learning by comparing the similarity between samples. Secondly, the task-based learning strategy can enable the model to continuously enhance its ability to learn how to learn with a large number of tasks randomly generated from different data sets. Benefitting from the above two points, the proposed method has excellent generalization ability and can obtain satisfactory classification results with only a few labeled samples. In order to verify the performance of the proposed method, experiments were carried out on three public data sets. The results indicate that the proposed method can achieve better classification results than the traditional semisupervised support vector machine and semisupervised deep learning models.

show abstract

Hyperspectral Image Classification Using CapsNet With Well-Initialized Shallow Layers

Cited by 51 publications

References 17 publications

Deep Induction Network for Small Samples Classification of Hyperspectral Images

Deep Induction Network for Small Samples Classification of Hyperspectral Images

Hyperspectral Image Classification With CapsNet and Markov Random Fields

Deep Relation Network for Hyperspectral Image Few-Shot Classification

Contact Info

Product

Resources

About