Preprint
Abstract
Recently, the first foundation model developed specifically for image segmentation tasks was developed, termed the "Segment Anything Model" (SAM). SAM can segment objects in input imagery based on cheap input prompts, such as one (or more) points, a bounding box, or a mask. The authors examined the \textit{zero-shot} image segmentation accuracy of SAM on a large number of vision benchmark tasks and found that SAM usually achieved recognition accuracy similar to, or sometimes exceeding, vision models that had been trained on the target tasks. The impressive generalization of SAM for segmentation has major implications for vision researchers working on natural imagery. In this work, we examine whether SAM's performance extends to overhead imagery problems and help guide the community's response to its development. We examine SAM's performance on a set of diverse and widely studied benchmark tasks. We find that SAM does often generalize well to overhead imagery, although it fails in some cases due to the unique characteristics of overhead imagery and its common target objects. We report on these unique systematic failure cases for remote sensing imagery that may comprise useful future research for the community.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- AquaSAM: Underwater Image Foreground Segmentation2024
- Recognize Anything: A Strong Image Tagging Model2024
- Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world ApplicationsMachine Intelligence Research, 2024
- CellViT: Vision Transformers for precise cell segmentation and classificationMedical Image Analysis, 2024
- Knowledge Distillation with Segment Anything (SAM) Model for Planetary Geological Mapping2024
- SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation2023
- Detect Any Shadow: Segment Anything for Video Shadow DetectionIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Road extraction in remote sensing data: A surveyInternational Journal of Applied Earth Observation and Geoinformation, 2022
- A Global Context-aware and Batch-independent Network for road extraction from VHR satellite imageryISPRS Journal of Photogrammetry and Remote Sensing, 2021
- Distributed solar photovoltaic array location and extent dataset for remote sensing object identificationScientific Data, 2016