Segmentation models perform a pixel-wise classification by classifying the pixels into different classes. The classified pixels correspond to different objects or regions in the image. These models have a wide variety of use cases across multiple domains. When used with satellite and aerial imagery, these models can help to identify features such as building footprints, roads, water bodies, crop fields, etc.Generally, every segmentation model needs to be trained from scratch using a dataset labeled with the objects of interest. This can be an arduous and time-consuming task. Meta's Segment Anything Model (SAM) is aimed at creating a foundational model that can be used to segment (as the name suggests) anything using zero-shot learning and generalize across domains without additional training. SAM is trained on the Segment Anything 1-Billion mask dataset (SA-1B) which comprises a diverse set of 11 million images and over 1 billion masks. This makes the model highly robust in identifying object boundaries and differentiating between various objects across domains, even though it might have never seen them before. Use this model to extract masks of various objects in any image.Using the modelFollow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS. Fine-tuning the modelThis model can be fine-tuned using SamLoRA architecture in ArcGIS. Follow the guide and refer to this sample notebook to fine-tune this model.Input8-bit, 3-band imagery.OutputFeature class containing masks of various objects in the image.Applicable geographiesThe model is expected to work globally.Model architectureThis model is based on the open-source Segment Anything Model (SAM) by Meta.Training dataThis model has been trained on the Segment Anything 1-Billion mask dataset (SA-1B) which comprises a diverse set of 11 million images and over 1 billion masks.Sample resultsHere are a few results from the model.

This dataset contains a daily snapshot of active exclusion records entered by the U.S. Federal government identifying those parties excluded from receiving Federal contracts, certain subcontracts, and certain types of Federal financial and non-financial assistance and benefits. The data was formerly contained in the Excluded Parties List System (EPLS). In July 2012, EPLS was incorporated into the System for Award Management (SAM). SAM is now the electronic, web-based system that keeps its user community aware of administrative and statutory exclusions across the entire government, and individuals barred from entering the United States. Users must read the exclusion record completely to understand how it impacts the excluded party. Note - Here is the link for the SAM Functional Data Dictionary - https://www.sam.gov/SAM/transcript/SAM_Functional_Data_Dictionary.pdf

Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use the well-learned knowledge of foundation models (e.g., SAM) to simplify the learning process. Recently, SAM 2 has extended SAM by supporting video segmentation, whose class-agnostic matching ability is useful to FSS. A simple idea is to encode support foreground (FG) features as memory, with which query FG features are matched and fused. Unfortunately, the FG objects in different frames of SAM 2's video data are always the same identity, while those in FSS are different identities, i.e., the matching step is incompatible. Therefore, we design Pseudo Prompt Generator to encode pseudo query memory, matching with query features in a compatible way. However, the memories can never be as accurate as the real ones, i.e., they are likely to contain incomplete query FG, but some unexpected query background (BG) features, leading to wrong segmentation. Hence, we further design Iterative Memory Refinement to fuse more query FG features into the memory, and devise a Support-Calibrated Memory Attention to suppress the unexpected query BG features in memory. Extensive experiments have been conducted on PASCAL-5i and COCO-20i to validate the effectiveness of our design, e.g., the 1-shot mIoU can be 4.2% better than the best baseline.

The SAM API is a RESTful method of retrieving public information about the businesses, organizations, or individuals (referred to as entities) within the SAM entity regsitration data set. Public registration information can currently be retrieved on an entity-by-entity basis. In addition, the SAM Search API offers both a 'quick search' and 'advanced search' method.

This work investigates the robustness of SAM to corruptions and adversarial attacks.

The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs). SAM excels in segmentation tasks across diverse domains, whereas CLIP is renowned for its zero-shot recognition capabilities. This paper presents an in-depth exploration of integrating these two models into a unified framework. Specifically, we introduce the Open-Vocabulary SAM, a SAM-inspired model designed for simultaneous interactive segmentation and recognition, leveraging two unique knowledge transfer modules: SAM2CLIP and CLIP2SAM. The former adapts SAM’s knowledge into the CLIP via distillation and learnable transformer adapters, while the latter transfers CLIP knowledge into SAM, enhancing its recognition capabilities. Extensive experiments on various datasets and detectors show the effectiveness of Open-Vocabulary SAM in both segmentation and recognition tasks, significantly outperforming the naïve baselines of simply combining SAM and CLIP. Furthermore, aided with image classification data training, our method can segment and recognize approximately 22,000 classes.

This dataset is from the City of Boston's Street Address Management (SAM) system, containing Boston addresses. Updated nightly and shared publicly.

Comprehensive dataset containing 52 verified SAM locations in United States with complete contact information, ratings, reviews, and location data.

The focus of this deployment is the collection of multiple acoustic datasets and water column parameters to be used toward assisting fish stock assessments

USF Sam Glider deployment in the North Atlantic Ocean (July 2021)

Subscribers can find out export and import data of 23 countries by HS code or product’s name. This demo is helpful for market analysis.

Comprehensive dataset containing 35 verified Sam's Place locations in United States with complete contact information, ratings, reviews, and location data.

Comprehensive dataset containing 29 verified Sam's Market locations in United States with complete contact information, ratings, reviews, and location data.

Traffic analytics, rankings, and competitive metrics for sam.gov as of September 2025

Comprehensive dataset containing 16 verified Sam locations in Poland with complete contact information, ratings, reviews, and location data.

This dataset provides information about the number of properties, residents, and average property values for Sam Friend Road cross streets in Accident, MD.

Find details of Sam Shamouilian Inc Buyer/importer data in US (United States) with product description, price, shipment date, quantity, imported products list, major us ports name, overseas suppliers/exporters name etc. at sear.co.in.

This dataset provides information about the number of properties, residents, and average property values for Magic Sam Court cross streets in Biltmore Lake, NC.

SAM2_AERO_PRF_NAT data are Stratospheric Aerosol Measurement (SAM) II - Aerosol Profiles in Native (NAT) Format which measure solar irradiance attenuated by aerosol particles in the Arctic and Antarctic stratosphere.The Stratospheric Aerosol Measurement (SAM) II experiment flew aboard the Nimbus 7 spacecraft and provided vertical profiles of aerosol extinction in both the Arctic and Antarctic polar regions. The SAM II data coverage began on October 29, 1978 and extended through December 18, 1993, until SAM II was no longer able to acquire the sun. The data coverage for the Antarctic region extends through December 18, 1993, and has one data gap for the period of time from mid-January through the end of October 1993. The data coverage for the Arctic region extends through January 7, 1991, and contains data gaps beginning in 1988 that increase in size each year due to an orbit degradation associated with the Nimbus-7 spacecraft.

Subscribers can find out export and import data of 23 countries by HS code or product’s name. This demo is helpful for market analysis.