A new spatial affinity component for self-supervised pretraining leverages high-resolution imagery to enhance mid-resolution satellite image representations and segmentation performance.
Masked autoencoders are scalable vision learners
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Task-guided triplet selection via mutual information improves multi-annotation representation learning over static weighting on an aerial wildlife dataset.
citing papers explorer
-
Cross-Scale Pretraining: Enhancing Self-Supervised Learning for Low-Resolution Satellite Imagery for Semantic Segmentation
A new spatial affinity component for self-supervised pretraining leverages high-resolution imagery to enhance mid-resolution satellite image representations and segmentation performance.
-
Task-Guided Multi-Annotation Triplet Learning for Remote Sensing Representations
Task-guided triplet selection via mutual information improves multi-annotation representation learning over static weighting on an aerial wildlife dataset.