TY - GEN
T1 - Aleatoric Uncertainty Embedded Transfer Learning for SEA-ICE Classification in SAR Images
AU - Liu, Ying
AU - Huang, Zhongling
AU - Han, Junwei
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Fine-grained sea-ice classification in SAR images is challenging due to the scarce labeled data and the imperfect annotation. Pre-training strategies are commonly carried out to prevent severe overfitting with limited labeled data. In spite of this, the observation noise still exists in the transferred features, which can be captured by aleatoric uncertainty. In this paper, we propose an aleatoric uncertainty embedded sea-ice classification method together with transfer learning of two different pre-training strategies. Instead of representing the transferred feature as a deterministic embedding, the proposed method concerns the feature uncertainty and models the embedding as a Gaussian distribution with variance. The experiments demonstrate that the proposed aleatoric uncertainty estimation is beneficial to improving the classification result of transfer learning. Based on the measured feature uncertainty, we analyze the potential of integrating two different pre-trained models to further enhance the performance.
AB - Fine-grained sea-ice classification in SAR images is challenging due to the scarce labeled data and the imperfect annotation. Pre-training strategies are commonly carried out to prevent severe overfitting with limited labeled data. In spite of this, the observation noise still exists in the transferred features, which can be captured by aleatoric uncertainty. In this paper, we propose an aleatoric uncertainty embedded sea-ice classification method together with transfer learning of two different pre-training strategies. Instead of representing the transferred feature as a deterministic embedding, the proposed method concerns the feature uncertainty and models the embedding as a Gaussian distribution with variance. The experiments demonstrate that the proposed aleatoric uncertainty estimation is beneficial to improving the classification result of transfer learning. Based on the measured feature uncertainty, we analyze the potential of integrating two different pre-trained models to further enhance the performance.
KW - Aleatoric uncertainty
KW - SAR image understanding
KW - Sea-ice classification
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85140366305&partnerID=8YFLogxK
U2 - 10.1109/IGARSS46834.2022.9883248
DO - 10.1109/IGARSS46834.2022.9883248
M3 - 会议稿件
AN - SCOPUS:85140366305
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 4980
EP - 4983
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 -