Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation

By Dengxin Dai, Wen Yang. 2011

367 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Representation & Self-Supervised Learning, Remote Sensing

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

1. Junwei Han
2. Gong Cheng
3. Liangpei Zhang
4. Xiaoqiang Lu
5. Xiang Bai
6. Yanfei Zhong
7. Dacheng Tao
8. Gui-Song Xia

In Media Technology

1. Gong Cheng
2. Junwei Han
3. Liangpei Zhang
4. Xiaoqiang Lu
5. Yanfei Zhong
6. Gui-Song Xia
7. Lei Guo
8. Wei Li

In Representation & Self-Supervised Learning

1. Liangpei Zhang
2. Gui-Song Xia
3. Yanfei Zhong
4. Jingwen Hu
5. Fan Hu
6. Xiaoqiang Lu
7. Gong Cheng
8. Junwei Han

In Remote Sensing

1. Liangpei Zhang
2. Yanfei Zhong
3. Wei Li
4. Gong Cheng
5. Junwei Han
6. Hongjun Su
7. Gui-Song Xia
8. Jingwen Hu

Citations in the corpus

• Self-Supervised Remote Sensing Feature Learning: Learning Paradigms, Challenges, and Future Works (2022, neutral): “[17], [18], [19], [20], autoencoder [21], [22], [23], [24], [25], [26], [27], [28], [29], [30], and deep belief networks [31].”
• Hierarchical Coding Vectors for Scene Level Land-Use Classification (2016, methodology): “A two-layer sparse coding method is used in [19].”
• Fusion of Deep Convolutional Neural Networks for Land Cover Classification of High-Resolution Imagery (2017, methodology): “The RSD is a 19 class high-resolution satellite image data set [19] that was evaluated in addition to the UCM data set.”
• Land-use scene classification using multi-scale completed local binary patterns (2016, methodology): “The second dataset used in our experiments is the 19-class satellite scene dataset [23].”
• Ieee Geoscience and Remote Sensing Letters Fusion of Global and Local Descriptors for Remote Sensing Image Classification (positive): “…between Gabor coefficients at different scales and the same orientation have been shown to correspond to center-surround organization (opponency) of the cells in human retina and used for texture [12] and satellite image classification [13], as well as target detection in satellite images [14].”
• Training Deep Convolutional Neural Networks for Land–Cover Classification of High-Resolution Imagery (2017, methodology): “In addition to the UCM data set, we evaluated another remote sensing image data set from [20] that includes 19 land– cover classes with at least 50 images/class.”
• Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning (2022, methodology): “Our analysis uses eight different land-use classification datasets: RESISC-45 [11], the UC Merced Land Use Dataset [65], AiRound and CV-BrCT [43], MLRSNet [48], EuroSAT [29], Optimal-31 [55], WHU-RS19 [14], SpaceNet v1 and v2 [53], and Functional Map of the World [12].”
• Unsupervised Deep Feature Extraction for Remote Sensing Image Classification (2015, background): “learned dictionaries for image pansharpening [34], saliencybased codes for segmentation [35], [36], sparse bag-of-words”
• AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification (2016, background): “- Locality-constrained Linear Coding (LLC) [85] is an effective coding scheme adapted from sparse coding methods [7, 17, 59].”
• Automatic Annotation of Satellite Images via Multifeature Joint Sparse Coding With Spatial Relation Constraint (2013, background): “If it is set to zero, our classification rule is degenerated to be the same with that of SRC and TSC. Algorithm II (Procedure of automatic annotation) Input: Feature dictionaries {Dk}Kk=1, image to be annotated I , tuning parameters λ, γ. 1.”
• Remote Sensing Image Scene Classification Using Multi-Scale Completed Local Binary Patterns and Fisher Vectors (2016, methodology): “The second dataset used in our experiments is the 19-class satellite scene dataset [29].”
• When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs (2018, methodology): “Typical unsupervised feature learning methods include, but not limited to, principal component analysis, k-means clustering, sparse coding [26]–[28], [33], [44] and autoencoder [29], [31].”
• Unsupervised Quaternion Feature Learning for Remote Sensing Image Classification (2016, methodology): “Sparse coding of SIFT descriptors is applied to satellite image classification in [18] and [19].”