Large Scale Masked Autoencoding for Reducing Label Requirements on SAR Data
Dec 15, 2023
Speakers
Matt Allen
Speaker · 0 followers
Francisco Dorr
Speaker · 0 followers
Joseph Alejandro Gallego Mejia
Speaker · 1 follower
Laura Martínez-Ferrer
Speaker · 0 followers
Anna Jungbluth
Speaker · 0 followers
Freddie Kalaitzis
Speaker · 1 follower
Raul Ramos-Pollán
Speaker · 0 followers
About
Satellite-based remote sensing is instrumental in the monitoring and mitigation of the effects of anthropogenic climate change. Large scale, high resolution data derived from these sensors can be used to inform intervention and policy decision making, but the timeliness and accuracy of these interventions is limited by use of optical data, which cannot operate at night and is affected by adverse weather conditions. Synthetic Aperture Radar (SAR) offers a robust alternative to optical data, but its associated complexities limit the scope of labelled data generation for traditional deep learning. In this work, we apply a self-supervised pretraining scheme, masked autoencoding, to SAR amplitude data covering 8.7% of the Earth's land surface area, and tune the pretrained weights on two downstream tasks crucial to monitoring climate change - vegetation cover prediction and land cover classification. We show that the use of this pretraining scheme reduces labelling requirements for the downstream tasks by more than an order of magnitude, and that this pretraining generalises geographically, with the performance gain increasing when tuned downstream on regions outside the pretraining set. Our findings significantly advance climate change mitigation by facilitating the development of task and region-specific SAR models, allowing local communities and organizations to deploy tailored solutions for rapid, accurate monitoring of climate change effects.Satellite-based remote sensing is instrumental in the monitoring and mitigation of the effects of anthropogenic climate change. Large scale, high resolution data derived from these sensors can be used to inform intervention and policy decision making, but the timeliness and accuracy of these interventions is limited by use of optical data, which cannot operate at night and is affected by adverse weather conditions. Synthetic Aperture Radar (SAR) offers a robust alternative to optical data, but i…
Organizer
NeurIPS 2023
Account · 645 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
Watch later
Zhongang Cai, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
Watch later
Ranran Shen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Tree Variational Autoencoders: Learning Hierarchical Latent Representations
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Normalization Layers Are All That Sharpness-Aware Minimization Needs
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Robust Model Reasoning and Fitting via Dual Sparsity Pursuit
Watch later
Xingyu Jiang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models
Watch later
Chenwei Wei, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%