Unsupervised Self-training Algorithm Based on Deep Learning for Optical Aerial Images Change Detection

by   Yuan Zhou, et al.

Optical aerial images change detection is an important task in earth observation and has been extensively investigated in the past few decades. Generally, the supervised change detection methods with superior performance require a large amount of labeled training data which is obtained by manual annotation with high cost. In this paper, we present a novel unsupervised self-training algorithm (USTA) for optical aerial images change detection. The traditional method such as change vector analysis is used to generate the pseudo labels. We use these pseudo labels to train a well designed convolutional neural network. The network is used as a teacher to classify the original multitemporal images to generate another set of pseudo labels. Then two set of pseudo labels are used to jointly train a student network with the same structure as the teacher. The final change detection result can be obtained by the trained student network. Besides, we design an image filter to control the usage of change information in the pseudo labels in the training process of the network. The whole process of the algorithm is an unsupervised process without manually marked labels. Experimental results on the real datasets demonstrate competitive performance of our proposed method.


page 1

page 3

page 5

page 7

page 8

page 9


Self-training with Noisy Student improves ImageNet classification

We present a simple self-training method that achieves 87.4 on ImageNet,...

Self-Training with Differentiable Teacher

Self-training achieves enormous success in various semi-supervised and w...

SLADE: A Self-Training Framework For Distance Metric Learning

Most existing distance metric learning approaches use fully labeled data...

Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection

Due to the high annotation cost of large-scale facial landmark detection...

Unsupervised Change Detection in Multi-temporal VHR Images Based on Deep Kernel PCA Convolutional Mapping Network

With the development of Earth observation technology, very-high-resoluti...

Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment

In the tasks of image aesthetic quality evaluation, it is difficult to r...

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model

This paper develops an unsupervised learning algorithm that trains a Dee...