IEEE Transactions on Geoscience and Remote Sensing· 2017Q1
Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework
- 1,871citations
- Q1SCImago
- 2017year
Short summary
A novel end-to-end spectral-spatial residual network (SSRN) classifies hyperspectral images using raw 3-D cubes, achieving state-of-the-art accuracy without manual feature engineering.
AI-generated from the title and abstract; the full text is not read.
Key points
- Designed an end-to-end spectral-spatial residual network (SSRN) for hyperspectral image classification.
- SSRN takes raw 3-D cubes as input, eliminating the need for feature engineering.
- Spectral and spatial residual blocks learn features from spectral signatures and spatial contexts.
- Identity mapping in residual blocks facilitates gradient backpropagation, addressing accuracy decline.
- Achieved state-of-the-art accuracy on Indian Pines, Kennedy Space Center, and University of Pavia datasets.
AI-generated from the title and abstract; the full text is not read.
Abstract
In this paper, we designed an end-to-end spectral-spatial residual network (SSRN) that takes raw 3-D cubes as input data without feature engineering for hyperspectral image classification. In this network, the spectral and spatial residual blocks consecutively learn discriminative features from abundant spectral signatures and spatial contexts in hyperspectral imagery (HSI). The proposed SSRN is a supervised deep learning framework that alleviates the declining-accuracy phenomenon of other deep learning models. Specifically, the residual blocks connect every other 3-D convolutional layer through identity mapping, which facilitates the backpropagation of gradients. Furthermore, we impose batch normalization on every convolutional layer to regularize the learning process and improve the classification performance of trained models. Quantitative and qualitative results demonstrate that the SSRN achieved the state-of-the-art HSI classification accuracy in agricultural, rural-urban, and urban data sets: Indian Pines, Kennedy Space Center, and University of Pavia.
The authors' abstract, as published at the source. IEEE Transactions on Geoscience and Remote Sensing, 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Media Technology
Media TechnologyEngineering