Label Noise Robust Image Representation Learning based on Supervised Variational Autoencoders in Remote Sensing
This work addresses label noise issues in remote sensing, which is crucial for improving data quality from publicly available sources, though it appears incremental as it builds on existing supervised variational autoencoder frameworks.
The paper tackles the problem of noisy labels in remote sensing image representation learning by proposing a method that combines a supervised variational autoencoder with deep neural networks to assign importance weights to training samples, reducing the impact of noisy labels. Experimental results demonstrate the method's effectiveness compared to existing label noise robust techniques.
Due to the publicly available thematic maps and crowd-sourced data, remote sensing (RS) image annotations can be gathered at zero cost for training deep neural networks (DNNs). However, such annotation sources may increase the risk of including noisy labels in training data, leading to inaccurate RS image representation learning (IRL). To address this issue, in this paper we propose a label noise robust IRL method that aims to prevent the interference of noisy labels on IRL, independently from the learning task being considered in RS. To this end, the proposed method combines a supervised variational autoencoder (SVAE) with any kind of DNN. This is achieved by defining variational generative process based on image features. This allows us to define the importance of each training sample for IRL based on the loss values acquired from the SVAE and the task head of the considered DNN. Then, the proposed method imposes lower importance to images with noisy labels, while giving higher importance to those with correct labels during IRL. Experimental results show the effectiveness of the proposed method when compared to well-known label noise robust IRL methods applied to RS images. The code of the proposed method is publicly available at https://git.tu-berlin.de/rsim/RS-IRL-SVAE.