TY - JOUR
T1 - Detecting Changes by Learning No Changes
T2 - Data-Enclosing-Ball Minimizing Autoencoders for One-Class Change Detection in Multispectral Imagery
AU - Mou, Lichao
AU - Hua, Yuansheng
AU - Saha, Sudipan
AU - Bovolo, Francesca
AU - Bruzzone, Lorenzo
AU - Zhu, Xiao Xiang
N1 - Publisher Copyright:
© 1980-2012 IEEE.
PY - 2022
Y1 - 2022
N2 - Change detection is a long-standing and challenging problem in remote sensing. Very often, features about changes are difficult to model beforehand, thus making the collection of changed samples a challenging task. In comparison, it is much easier to collect numerous no-change samples. It is possible to define a change detection approach using only easily available annotated no-change samples, which we henceforth call one-class change detection. Autoencoder networks being trained on no-change data are natural candidates for addressing this task due to their superior performance when compared with other one-class classification models. However, the autoencoders usually suffer from the problem of overgeneralization, i.e., they tend to generalize too well, thus risking properly reconstructing changed samples. In this article, we propose a novel data-enclosing-ball minimizing autoencoder (DebM-AE) that is trained with dual objectives - a reconstruction error criterion and a minimum volume criterion. The network learns a compact latent space, where encodings of no-change samples have low intraclass variance, which as counterpart has the identification of changed instances. We conducted extensive experiments on three real-world datasets. Results demonstrate advantages of the proposed method over other competitors. We make our data and code publicly available (https://gitlab.lrz.de/ai4eo/reasoning/DebM-AE; https://github.com/lcmou/DebM-AE).
AB - Change detection is a long-standing and challenging problem in remote sensing. Very often, features about changes are difficult to model beforehand, thus making the collection of changed samples a challenging task. In comparison, it is much easier to collect numerous no-change samples. It is possible to define a change detection approach using only easily available annotated no-change samples, which we henceforth call one-class change detection. Autoencoder networks being trained on no-change data are natural candidates for addressing this task due to their superior performance when compared with other one-class classification models. However, the autoencoders usually suffer from the problem of overgeneralization, i.e., they tend to generalize too well, thus risking properly reconstructing changed samples. In this article, we propose a novel data-enclosing-ball minimizing autoencoder (DebM-AE) that is trained with dual objectives - a reconstruction error criterion and a minimum volume criterion. The network learns a compact latent space, where encodings of no-change samples have low intraclass variance, which as counterpart has the identification of changed instances. We conducted extensive experiments on three real-world datasets. Results demonstrate advantages of the proposed method over other competitors. We make our data and code publicly available (https://gitlab.lrz.de/ai4eo/reasoning/DebM-AE; https://github.com/lcmou/DebM-AE).
KW - Autoencoder network
KW - change detection
KW - one-class classification
KW - remote sensing
UR - http://www.scopus.com/inward/record.url?scp=85137581868&partnerID=8YFLogxK
U2 - 10.1109/TGRS.2022.3200985
DO - 10.1109/TGRS.2022.3200985
M3 - Article
AN - SCOPUS:85137581868
SN - 0196-2892
VL - 60
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
M1 - 5629716
ER -