Enabling Training-Free Text-Based Remote Sensing Segmentation

TL;DR

This work proposes a simple yet effective approach that integrates contrastive and generative VLMs with the Segment Anything Model (SAM), enabling a fully training-free or lightweight LoRA-tuned pipeline.

Abstract

Recent advances in Vision Language Models (VLMs) and Vision Foundation Models (VFMs) have opened new opportunities for zero-shot text-guided segmentation of remote sensing imagery. However, most existing approaches still rely on additional trainable components, limiting their generalisation and practical applicability. In this work, we investigate to what extent text-based remote sensing segmentation can be achieved without additional training, by relying solely on existing foundation models. We propose a simple yet effective approach that integrates contrastive and generative VLMs with the Segment Anything Model (SAM), enabling a fully training-free or lightweight LoRA-tuned pipeline. Our contrastive approach employs CLIP as mask selector for SAM's grid-based proposals, achieving state-of-the-art open-vocabulary semantic segmentation (OVSS) in a completely zero-shot setting. In parallel, our generative approach enables reasoning and referring segmentation by generating click prompts for SAM using GPT-5 in a zero-shot setting and a LoRA-tuned Qwen-VL model, with the latter yielding the best results. Extensive experiments across 19 remote sensing benchmarks, including open-vocabulary, referring, and reasoning-based tasks, demonstrate the strong capabilities of our approach. Code will be released at https://github.com/josesosajs/trainfree-rs-segmentation.

Figures (11)

• Figure 1: Existing methods li2025segearthli2025segearth-r1shabbir2025geopixel rely on additional trainable mask decoders and adapters. We propose a training-free methodology that combines VLMs and SAM without introducing new trainable components. Additionally, with LoRA fine-tuning, our method achieves state-of-the-art performance on reasoning segmentation. Blue is for frozen components.
• Figure 2: Inference schemes of our segmentation approaches with (a) contrastive and (b) generative VLMs.
• Figure 3: Qualitative results of the training-free contrastive VLM pipeline on multi-class (first and second rows) and single-class (third row) OVSS tasks using remote sensing datasets.
• Figure 4: Qualitative results of the LoRA-tuned generative VLM pipeline on reasoning (first and second rows) and referring (third row) tasks using remote sensing datasets.
• Figure 5: Visualisations from click generation procedure. Masks (red) are produced by SAM prompted by clicks (green). Reported IoU is compared to groung truth mask.