Supervised learning algorithms predominate over all other land cover mapping/monitoring techniques that use remote sensing (RS) data. However, the performance of supervised learning algorithms varies as a function of labeled training data properties, such as the sample size and the statistically unbiased and discriminative capabilities of the features extracted from the data. As monitoring requires multi-temporal images, radiometric differences, atmospheric and illumination conditions, seasonal variations, and variable acquisition geometries can affect supervised techniques, potentially causing a distribution shift in the training data. Regardless of the cause, any distribution change or domain shift that occurs after learning a classifier can degrade performance.
In the pattern recognition (PR) and RS image classification communities, this challenge is commonly referred to as covariate shift or sample selection bias. Recently, domain adaptation (DA) techniques, which attempt to mitigate performance the degradation caused by a distribution shift, has attracted increasing attention and is widely considered to provide an efficient solution. However, most previous studies have assumed that data from different domains are represented by the same types of features with the same dimensions. Thus, these techniques cannot handle the problem of data from source and target domains represented by heterogeneous features with different dimensions. One example of this scenario is land cover updating using current RS data; each time, there are different features with finer spatial resolution and more spectral bands (e.g., Landsat 8 OLI with nine spectral bands at 15–30 m spatial resolution, and AVIRIS with 224 spectral bands at 20 m spatial resolution), when the training data are only available at coarser spatial and spectral resolutions (e.g., MSS with four spectral bands and 60 m spatial resolution).
To this end, Alim Samt, a team member of scientist group from the Xinjiang Institute of Ecology and Geography led by Jilili Abuduwaili, proposed novel techniques to address heterogeneous domain adaptation problems, i.e., situations in which the data to be processed and recognized are collected from different heterogeneous domains.
The novel techniques are supervised multi-view canonical correlation analysis ensemble and its semi-supervised version. Specifically, the multi-view canonical correlation analysis scheme is utilized to extract multiple correlation subspaces that are useful for joint representations for data association across domains. This scheme makes homogeneous domain adaption algorithms suitable for heterogeneous domain adaptation problems. The experimental results confirm that multi-view canonical correlation can overcome the limitations of SVCCA. Both of the proposed procedures outperform the ones used in the comparison with respect to not only the classification accuracy but also the computational efficiency.
The research was published in Remote Sensing entitled with “Supervised and Semi-Supervised Multi-View Canonical Correlation Analysis Ensemble for Heterogeneous Domain Adaptation in Remote Sensing Image Classification”.