# Label Less, Learn More: Resource-Efficient Active Semi-Supervised Learning for Onboard Satellite Image Annotation

arXiv: https://arxiv.org/abs/2609.37481 · HTML: https://mlsanity.com/paper/2609.37481/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2306.11300/) (2023)
- [PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval](https://mlsanity.com/paper/1706.03424/) (2017)
- [Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment](https://mlsanity.com/paper/2312.06960/) (2023)
- [Multimodal Fusion Transformer for Remote Sensing Image Classification](https://mlsanity.com/paper/2203.16952/) (2022)
- [Active learning for data streams: a survey](https://mlsanity.com/paper/2302.08893/) (2023)
- [GLH-Water: A Large-Scale Dataset for Global Surface Water Detection in Large-Size Very-High-Resolution Satellite Imagery](https://mlsanity.com/paper/2303.09310/) (2023)
- [Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models](https://mlsanity.com/paper/2409.03901/) (2024)
- [Stitching Satellites to the Edge: Pervasive and Efficient Federated LEO Satellite Learning](https://mlsanity.com/paper/2401.15541/) (2024)
- [Decentralised Semi-supervised Onboard Learning for Scene Classification in Low-Earth Orbit](https://mlsanity.com/paper/2305.04059/) (2023)
- [TinyML Enhances CubeSat Mission Capabilities](https://mlsanity.com/paper/2603.20174/) (2026)
- [FitNets: An Adaptive Framework to Learn Accurate Traffic Distributions](https://mlsanity.com/paper/2405.10931/) (2024)
- [Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification](https://mlsanity.com/paper/2411.00209/) (2024)
- [Enabling Near-realtime Remote Sensing via Satellite-Ground Collaboration of Large Vision-Language Models](https://mlsanity.com/paper/2510.24242/) (2025)

## Abstract (arXiv)

Large-scale pervasive sensing increasingly relies on high-resolution satellite imagery, yet task-specific onboard vision is constrained by costly annotation and limited computation, memory, energy, and communication resources. Existing approaches largely rely on either data-hungry supervised learning or large vision-language foundation models, limiting efficient adaptation and deployment under these constraints. We present SatLabel, a resource-aware learning framework that transforms limited satellite labels into progressively refined onboard models through adaptive sample acquisition and semi-supervised model adaptation. Rather than repeatedly training on uniformly sampled labels, SatLabel closes the loop between model uncertainty, class imbalance, and pseudo-label quality to selectively acquire informative samples while exploiting abundant unlabeled imagery. This enables a compact student to adapt to target sensing domains with reduced annotation and inference costs. We further introduce an optional Mixture-of-Experts (MoE) student with graph-based feature refinement to enhance representation capacity while retaining a lightweight footprint. We evaluate SatLabel on 11 remote-sensing datasets spanning core, extended, and unseen domains against RemoteCLIP zero-shot inference. SatLabel improves Macro-F1 on most core and extended datasets while maintaining strong cross-dataset transfer to unseen domains. More importantly, the Balanced student contains only 11.2 M parameters and occupies approximately 42.8 MB, compared with 151.3M parameters and 577 MB for RemoteCLIP, while requiring 3.65 versus 5.89 GFLOPs. Across four efficiency benchmarks, it achieves approximately 2x higher GPU-forward throughput and reduces energy per image on datasets.