🤖 AI Summary
To address the low efficiency and poor generalizability of interactive segmentation in complex remote sensing scenes, this paper proposes a click-guided Cascaded Forward Refinement (CFR) inference framework that iteratively optimizes segmentation results without manual intervention. We introduce RS-Click—the first click-based interactive segmentation benchmark specifically designed for remote sensing—covering diverse land-cover types, spatial scales, and spectral band combinations. We further develop SimpleClick-CFR, a lightweight and efficient model that significantly outperforms existing methods on RS-Click. Concurrently, we release SegMap, an open-source online tool enabling adjustable parameters, swappable models, and adaptable tasks for interactive remote sensing analysis. This work establishes, for the first time, a systematic evaluation framework for click-based remote sensing segmentation, bridging the gap between laboratory research and real-world deployment of interactive interpretation systems.
📝 Abstract
Interactive segmentation, a computer vision technique where a user provides guidance to help an algorithm segment a feature of interest in an image, has achieved outstanding accuracy and efficient human-computer interaction. However, few studies have discussed its application to remote sensing imagery, where click-based interactive segmentation could greatly facilitate the analysis of complicated landscapes. This study aims to bridge the gap between click-based interactive segmentation and remote sensing image analysis by conducting a benchmark study on various click-based interactive segmentation models. We assessed the performance of five state-of-the-art interactive segmentation methods (Reviving Iterative Training with Mask Guidance for Interactive Segmentation (RITM), FocalClick, SimpleClick, Iterative Click Loss (ICL), and Segment Anything (SAM)) on two high-resolution aerial imagery datasets. The Cascade-Forward Refinement (CFR) approach, an innovative inference strategy for interactive segmentation, was also introduced to enhance the segmentation results without requiring manual efforts. We further integrated CFR into all models for comparison. The performance of these methods on various land cover types, different object sizes, and multiple band combinations in the datasets was evaluated. The SimpleClick-CFR model consistently outperformed the other methods in our experiments. Building upon these findings, we developed a dedicated online tool called SegMap for interactive segmentation of remote sensing data. SegMap incorporates a well-performing interactive model that is fine-tuned with remote sensing data. Unlike existing interactive segmentation tools, SegMap offers robust interactivity, modifiability, and adaptability to analyze remote sensing imagery.