AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Data-Efficient ConvNeXt Pretraining for High-Resolution Sentinel-1 GRD SAR Representation Learning

arXiv · AI, language, vision and robotics · article · Oct 15, 2026 · UTC

Labeled Sentinel-1 Ground Range Detected (S1GRD) datasets remain scarce, limiting supervised deep learning for land-surface remote sensing, while self-supervised pretraining for this domain has been dominated by Vision Transformer (ViT)-based masked image modeling requiring substantial data and compute. We propose SparK-SAR, a sparse convolutional masked pretraining framework built on SparK and ConvNeXt, designed to exploit convolutional inductive biases for S1GRD imagery under constrained compute. SparK-SAR makes three core technical contributions: (i) ConvNeXt-RS, a domain-adapted encoder th

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-10-17T14:52:22.282Z. This is not the publication date.