Self Supervised Learning for Few Shot Hyperspectral Image Classification
By Nassim Ait Ali Braham, Lichao Mou, Jocelyn Chanussot, Julien Mairal, Xiao Xiang Zhu. 2022
14 citations recorded by the source corpus.
Deep learning has proven to be a very effective approach for Hyperspectral Image (HSI) classification. However, deep neural networks require large annotated datasets to generalize well. This limits the applicability of deep learning for HSI classification, where manually labelling thousands of pixels for every scene is impractical. In this paper, we propose to leverage Self Supervised Learning (SSL) for HSI classification. We show that by pre-training an encoder on unlabeled pixels using Barlow-Twins, a state-of-the-art SSL algorithm, we can obtain accurate models with a handful of labels. Experimental results demonstrate that this approach significantly outperforms vanilla supervised learning.
Subfields: Computer Vision and Pattern Recognition, Media Technology
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
- Valerio Marsocci
- Simone Scardapane
- Conrad M. Albrecht
- Xiao Xiang Zhu
- Nassim Ait Ali Braham
- Yi Wang
- Lichao Mou
- Laura Palagi
In Media Technology
- Simone Scardapane
- Valerio Marsocci
- Conrad M. Albrecht
- Xiao Xiang Zhu
- Nassim Ait Ali Braham
- Yi Wang
- Lichao Mou
- Zhenwei Shi
Citations in the corpus
- Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation (2022, methodology): “and BT was based on the current RS literature on SSL [11], [13], [20], [21], [22], and CV more in general [7], [8], [16], [23].”
- Self-Supervised Learning in Remote Sensing: A review (2022, methodology): “[227] used Barlow Twins for few-shot HSI classification in a two-stage approach.”