Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking

By Qi Wang, Jianzhe Lin, Yuan Yuan. IEEE Transactions on Neural Networks and Learning Systems, 2016

429 citations recorded by the source corpus.

Saliency detection has been a hot topic in recent years, and many efforts have been devoted in this area. Unfortunately, the results of saliency detection can hardly be utilized in general applications. The primary reason, we think, is unspecific definition of salient objects, which makes that the previously published methods cannot extend to practical applications. To solve this problem, we claim that saliency should be defined in a context and the salient band selection in hyperspectral image (HSI) is introduced as an example. Unfortunately, the traditional salient band selection methods suffer from the problem of inappropriate measurement of band difference. To tackle this problem, we propose to eliminate the drawbacks of traditional salient band selection methods by manifold ranking. It puts the band vectors in the more accurate manifold space and treats the saliency problem from a novel ranking perspective, which is considered to be the main contributions of this paper. To justify the effectiveness of the proposed method, experiments are conducted on three HSIs, and our method is compared with the six existing competitors. Results show that the proposed method is very effective and can achieve the best performance among the competitors.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f7a6be26eff0698df6fcb6fdaad79715699fc8cd

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Hyperspectral Band Selection: A Review (2019, methodology): “In [139], the manifold ranking algorithm combined clustering and ranking schemes to select dissimilar bands here, the k-means algorithm was employed to cluster all bands, and representative bands of each cluster were chosen by clone selection and treated as queries.”
Deep learning architecture for air quality predictions (2016, background): “Each hidden layer is a higher-level abstraction of the previous layer, and the last hidden layer contains high-level structure and representative information of the input, which are more effective for the successive prediction (Wang et al. 2016).”
Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network (2017, positive): “…emerged deeper models, such as ResNet [39] and Inception-V4 [40], achieved a higher score in many vision tasks, VGG networks have clear structures and compact memory requirements, which can be easily extended and applied, so we chose the 16-layered VGG network as our basic network architecture.”
Deep Few-Shot Learning for Hyperspectral Image Classification (2019, methodology): “In addition, band-selection methods [18], [19] are also applied in HSI to reduce feature dimensions.”
Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework (2018, methodology): “For instance, [9] adopted manifold ranking as an unsupervised feature selection method, which chooses the most representative bands for training the classifiers that follow.”
Recent Advances of Hyperspectral Imaging Technology and Applications in Agriculture (2020, background): “, bands) and is robust to noisy bands [160], and a manifold ranking‐based salient band selection method that puts band vectors in manifold space and selects a band‐based ranking that can tackle the problem of inappropriate measurement of the band difference [161].”
Hyperspectral Imaging: A Review on UAV-Based Sensors, Data Processing and Applications for Agriculture and Forestry (2017, methodology): “For saliency detection regarding to band selection in HSI, a manifold ranking approach—that is also extended to DL—is presented in [119].”
Hyperspectral Image Classification With Deep Learning Models (2018, methodology): “[7] propose a manifold ranking-based salient selection method for hyperspectral image classification.”
Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition (2017, methodology): “, the works [23]–[25] for HSI classification task and the works [26] and[27] for band selection task.”
Optimal Clustering Framework for Hyperspectral Band Selection (2018, methodology): “Greedy-based methods [21], [34], [35] greedily select or remove one band from the candidate band subset, and”
HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification (2019, background): “selection [13], weighted Markov random fields [14], and etc.”
Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art (2017, methodology): “In the approaches of [35], manifold learning was exploited for feature extraction and salient band selection of HSIs.”