TY - GEN
T1 - Self Supervised Learning for Few Shot Hyperspectral Image Classification
AU - Braham, Nassim Ait Ali
AU - Mou, Lichao
AU - Chanussot, Jocelyn
AU - Mairal, Julien
AU - Zhu, Xiao Xiang
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Few Shot Classification
KW - Hyperspectral Image Classification
KW - Self Supervised Learning
UR - http://www.scopus.com/inward/record.url?scp=85133826858&partnerID=8YFLogxK
U2 - 10.1109/IGARSS46834.2022.9884494
DO - 10.1109/IGARSS46834.2022.9884494
M3 - Conference contribution
AN - SCOPUS:85133826858
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 267
EP - 270
BT - IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
Y2 - 17 July 2022 through 22 July 2022
ER -