Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images

TL;DR

This paper introduces SegEarth-OV, a novel framework for annotation-free open-vocabulary segmentation of remote sensing images, effectively handling scale variations and fine details without manual annotations, and extends to SAR images via knowledge distillation.

Contribution

The paper presents SegEarth-OV, the first annotation-free open-vocabulary segmentation framework for RS images, and introduces AlignEarth for cross-modal knowledge transfer to SAR data.

Findings

Significant performance improvements over state-of-the-art methods.

Effective handling of scale variations and fine details in RS images.

Successful extension to SAR images using knowledge distillation.

Abstract

Semantic segmentation of remote sensing (RS) images is pivotal for comprehensive Earth observation, but the demand for interpreting new object categories, coupled with the high expense of manual annotation, poses significant challenges. Although open-vocabulary semantic segmentation (OVSS) offers a promising solution, existing frameworks designed for natural images are insufficient for the unique complexities of RS data. They struggle with vast scale variations and fine-grained details, and their adaptation often relies on extensive, costly annotations. To address this critical gap, this paper introduces SegEarth-OV, the first framework for annotation-free open-vocabulary segmentation of RS images. Specifically, we propose SimFeatUp, a universal upsampler that robustly restores high-resolution spatial details from coarse features, correcting distorted target shapes without any task-specific post-training. We also present a simple yet effective Global Bias Alleviation operation to subtract the inherent global context from patch features, significantly enhancing local semantic fidelity. These components empower SegEarth-OV to effectively harness the rich semantics of pre-trained VLMs, making OVSS possible in optical RS contexts. Furthermore, to extend the framework's universality to other challenging RS modalities like SAR images, where large-scale VLMs are unavailable and expensive to create, we introduce AlignEarth, which is a distillation-based strategy and can efficiently transfer semantic knowledge from an optical VLM encoder to an SAR encoder, bypassing the need to build SAR foundation models from scratch and enabling universal OVSS across diverse sensor types. Extensive experiments on both optical and SAR datasets validate that SegEarth-OV can achieve dramatic improvements over the SOTA methods, establishing a robust foundation for annotation-free and open-world Earth observation.