# Training-Free Entity-Level Few-Shot Segmentation of Remote Sensing Images with Advection Refinement

arXiv: https://arxiv.org/abs/2607.29278 · HTML: https://mlsanity.com/paper/2607.29278/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [A Simple Framework for Open-Vocabulary Segmentation and Detection](https://mlsanity.com/paper/2303.08131/) (2023)
- [iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images](https://mlsanity.com/paper/1905.12886/) (2019)
- [Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models](https://mlsanity.com/paper/1807.05713/) (2018)
- [ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2408.04883/) (2024)
- [Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2404.08181/) (2024)
- [Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation](https://mlsanity.com/paper/2411.09219/) (2024)
- [PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask](https://mlsanity.com/paper/2109.13788/) (2021)
- [Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining](https://mlsanity.com/paper/2401.08407/) (2024)
- [ResCLIP: Residual Attention for Training-free Dense Vision-language Inference](https://mlsanity.com/paper/2411.15851/) (2024)
- [Unified Open-World Segmentation with Multi-Modal Prompts](https://mlsanity.com/paper/2510.10524/) (2025)

## Abstract (arXiv)

Existing cross-domain few-shot segmentation approaches suffer from high training costs due to source-domain episodic training and pixel-wise dense prediction, while often producing fragmented and noisy predictions. To overcome these issues, we propose a training-free entity-level few-shot segmentation framework for remote sensing images with advection refinement. Specifically, we first leverage SAM3's generic geometric priors to generate category-agnostic entity primitives. By reformulating few-shot inference from pixel-level prediction to entity-level reasoning, foreground and background prototypes are constructed and combined with dense textual semantic responses from SAM3 to build a multi-modal semantic potential field. Furthermore, an advection equation-based semantic refinement mechanism is introduced to propagate category-aware information across both feature and similarity spaces, enhancing semantic continuity and suppressing local texture noise. Extensive experiments on multiple remote sensing datasets demonstrate that the proposed framework effectively mitigates domain shift and local noise, substantially improving SAM3's adaptation capability for remote sensing few-shot segmentation without additional training. Our code will be publicly available at https://github.com/yu-ni1989/ELFSS-AR.