CONTRASTIVE SELF-SUPERVISED DATA FUSION FOR SATELLITE IMAGERY

نویسندگان

چکیده

Abstract. Self-supervised learning has great potential for the remote sensing domain, where unlabelled observations are abundant, but labels hard to obtain. This work leverages multi-modal data augmentation-free contrastive self-supervised learning. Deep neural network models trained maximize similarity of latent representations obtained with different techniques from same location, while distinguishing them other locations. We showcase this idea two fusion methods and compare against standard supervised approaches on a land-cover classification task. Our results show that is powerful technique train image encoders capable producing meaningful representations: Simple linear probing performs par fully fine-tuning as little 10% labelled in higher accuracy than training entire dataset.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Self-supervised Approach for Fully Automated Urban Land Cover Classification of High-resolution Satellite Imagery

Commercially available high-resolution satellite imagery from sensors such as IKONOS and QuickBird are important data sources for a variety of urban area applications including infrastructure feature extraction and land cover mapping. Land cover maps from medium and high-resolution imagery are typically generated through supervised spectral classification of multispectral imagery. Supervised cl...

متن کامل

Time-Contrastive Networks: Self-Supervised Learning from Video

We propose a self-supervised approach for learning representations and robotic behaviors entirely from unlabeled videos recorded from multiple viewpoints, and study how this representation can be used in two robotic imitation settings: imitating object interactions from videos of humans, and imitating human poses. Imitation of human behavior requires a viewpoint-invariant representation that ca...

متن کامل

Fusion-Reflection Self-Supervised Learning

By analyzing learning from the perspective of knowledge acquisition , a number of common limitations are overcome. Modeling efficacy is proposed as an empirical measure of knowledge, providing a concrete, mathematical means of “acquiring knowledge” via gradient ascent. A specific network architecture is described, a hierarchical analog of node-labeled Hidden Markov Models, and its evaluation an...

متن کامل

A Method of Panchromatic Image Modification for Satellite Imagery Data Fusion

The standard ratio of spatial resolution between bands for high resolution satellites is 1:4, which is typical when combining images obtained from the same sensor. However, the cost of simultaneously purchasing a set of panchromatic and multispectral images is still relatively high. There is therefore a need to develop methods of data fusion of very high resolution panchromatic imagery with low...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

سال: 2022

ISSN: ['2194-9042', '2194-9050', '2196-6346']

DOI: https://doi.org/10.5194/isprs-annals-v-3-2022-705-2022