DNN-based PolSAR image classification on noisy labels
Deep neural networks (DNNs) appear to be a solution for the classification of polarimetric synthetic aperture radar (PolSAR) data in that they outperform classical supervised classifiers under the condition of sufficient training samples. The design of a classifier is challenging because DNNs can ea...
| Authors: | , , , , , |
|---|---|
| Format: | article |
| Publication Date: | 2022 |
| Country: | España |
| Institution: | Universitat Politècnica de Catalunya (UPC) |
| Repository: | UPCommons. Portal del coneixement obert de la UPC |
| Language: | English |
| OAI Identifier: | oai:upcommons.upc.edu:2117/368203 |
| Online Access: | https://hdl.handle.net/2117/368203 https://dx.doi.org/10.1109/JSTARS.2022.3168799 |
| Access Level: | Open access |
| Keyword: | Neural networks (Computer science) Synthetic aperture radar Remote sensing Deep neural network (DNN) Image classification Noisy label Polarimetric synthetic aperture radar (SAR) Xarxes neuronals (Informàtica) Radar d'obertura sintètica Teledetecció Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Radiocomunicació i exploració electromagnètica::Teledetecció |
| Summary: | Deep neural networks (DNNs) appear to be a solution for the classification of polarimetric synthetic aperture radar (PolSAR) data in that they outperform classical supervised classifiers under the condition of sufficient training samples. The design of a classifier is challenging because DNNs can easily overfit due to limited remote sensing training samples and unavoidable noisy labels. In this article, a softmax loss strategy with antinoise capability, namely, the probability-aware sample grading strategy (PASGS), is developed to overcome this limitation. Combined with the proposed softmax loss strategy, two classical DNN-based classifiers are implemented to perform PolSAR image classification to demonstrate its effectiveness. In this framework, the difference distribution implicitly reflects the probability that a training sample is clean, and clean labels can be distinguished from noisy labels according to the method of probability statistics. Then, this probability is employed to reweight the corresponding loss of each training sample during the training process to locate the noisy data and to prevent participation in the loss calculation of the neural network. As the number of training iterations increases, the condition of the probability statistics of the noisy labels will be constantly adjusted without supervision, and the clean labels will eventually be identified to train the neural network. Experiments on three PolSAR datasets with two DNN-based methods also demonstrate that the proposed method is superior to state-of-the-art methods. |
|---|