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.

Sam2

## Overview

Sam2 is a dataset for instance segmentation tasks - it contains Building annotations for 1,795 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Sam2 Vegatables

## Overview

Sam2 Vegatables is a dataset for instance segmentation tasks - it contains Vegatable 10 annotations for 319 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

VIRESET

VIRESET is a high-quality video instance editing dataset that provides temporally consistent and precise instance masks. Built upon the foundation of SA-V, VIRESET leverages the pretrained SAM-2 model to enhance the mask annotations from 6 FPS to 24 FPS, further enriched with detailed prompt-based annotations using PLLaVA. This dataset is used in the paper VIRES: Video Instance Repainting with Sketch and Text Guidance. Project page Code: https://github.com/suimuc/VIRES The… See the full description on the dataset page: https://huggingface.co/datasets/suimu/VIRESET.

Visual comparison of 100 human annotations (labels) compared with Segment Anything Model 2 (SAM2) segmentation.

physics-from-video/sam2-tracking dataset hosted on Hugging Face and contributed by the HF Datasets community

Sam2 Yolo11

## Overview

Sam2 Yolo11 is a dataset for instance segmentation tasks - it contains Beet Carrot annotations for 335 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Rust Sam2 20250628

## Overview

Rust Sam2 20250628 is a dataset for instance segmentation tasks - it contains Rust O0os annotations for 1,974 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

KImyaydd/sam2 dataset hosted on Hugging Face and contributed by the HF Datasets community

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.

Dataset

This dataset was created by liukunshan2

Released under MIT

Contents

Example Dataset (Tracking SAM2)

## Overview

Example Dataset (Tracking SAM2) is a dataset for instance segmentation tasks - it contains Fish annotations for 450 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

These figures are the graphical results of my Master 2 internship on automatic segmentation using SAM2(Segment Anything Model 2) an artificial intelligence. The red line represents the best cell line from which anatomical measurements were made.

hf-internal-testing/sam2-fixtures dataset hosted on Hugging Face and contributed by the HF Datasets community

The dataset contains:

.
├── images
├── masks
└── train.csv

• Images – This folder contains 588 RGB images showcasing various types of leaf diseases.
• Masks – This folder holds 588 RGBA segmentation masks, where the diseased regions of the leaves are annotated.
• train.csv – A CSV file that maps each image to its corresponding segmentation mask, ensuring proper indexing for SAM2 training.

Original Dataset - kaggle.com/datasets/sovitrath/leaf-disease-segmentation

physics-from-video/OLD-sam2-real-world-tracking dataset hosted on Hugging Face and contributed by the HF Datasets community

adarshh9/finetuned-sam2-predictions dataset hosted on Hugging Face and contributed by the HF Datasets community

The SAM II instrument, aboard the Earth-orbiting Nimbus 7 spacecraft, was designed to measure solar irradiance attenuated by aerosol particles in the Arctic and Antarctic stratosphere. This dataset collection contains 14 years of polar Arctic and Antarctic aerosol extinction profiles, atmospheric temperature and pressure data obtained from the Stratospheric Aerosol Instrument II (SAM II) on the NIMBUS 7 satellite.

Stratospheric Aerosol Measurement II - Aerosol Profile - Native format which measures solar irradiance attenuated by aerosol particles in the Arctic & Antarctic stratosphere.

Yash Sam 2.0

## Overview

Yash Sam 2.0 is a dataset for instance segmentation tasks - it contains Yash annotations for 734 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).