An End-to-End Joint Unsupervised Learning of Deep Model and Pseudo-Classes for Remote Sensing Scene Representation

TL;DR

This paper presents a novel end-to-end deep unsupervised learning approach using CNNs and pseudo-classes for remote sensing scene representation, effectively learning discriminative features without labeled data.

Contribution

It introduces a joint learning framework with pseudo-center loss and pseudo softmax loss, enabling CNNs to learn from pseudo labels in an unsupervised manner.

Findings

Outperforms state-of-the-art methods on remote sensing datasets.

Effectively learns discriminative scene representations without supervision.

Demonstrates robustness across different remote sensing datasets.

Abstract

This work develops a novel end-to-end deep unsupervised learning method based on convolutional neural network (CNN) with pseudo-classes for remote sensing scene representation. First, we introduce center points as the centers of the pseudo classes and the training samples can be allocated with pseudo labels based on the center points. Therefore, the CNN model, which is used to extract features from the scenes, can be trained supervised with the pseudo labels. Moreover, a pseudo-center loss is developed to decrease the variance between the samples and the corresponding pseudo center point. The pseudo-center loss is important since it can update both the center points with the training samples and the CNN model with the center points in the training process simultaneously. Finally, joint learning of the pseudo-center loss and the pseudo softmax loss which is formulated with the samples and the pseudo labels is developed for unsupervised remote sensing scene representation to obtain discriminative representations from the scenes. Experiments are conducted over two commonly used remote sensing scene datasets to validate the effectiveness of the proposed method and the experimental results show the superiority of the proposed method when compared with other state-of-the-art methods.