Papers with Code 아카이브

Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
1
평가표
5
보존된 평가 기록
6

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

Microscopy Image Dataset of Pulmonary Vascular Changes

Pulmonary hypertension (PH) is a syndrome complex that accompanies a number of diseases of different etiologies, associated with basic mechanisms of structural and functional changes of the pulmonary circulation vessels and revealed pressure increasing in the pulmonary artery. The structural changes in the pulmonary circulation vessels are the main limiting factor determining the prognosis of patients with PH. Thickening and irreversible deposition of collagen in the pulmonary artery branches walls leads to rapid disease progression and a therapy effectiveness decreasing. In this regard, histological examination of the pulmonary circulation vessels is critical both in preclinical studies and clinical practice. However, measurements of quantitative parameters such as the average vessel outer diameter, the vessel walls area, and the hypertrophy index claimed significant time investment and the requirement for specialist training to analyze micrographs. A dataset of pulmonary circulation vessels for pathology assessment using semantic segmentation techniques based on deep-learning is presented in this work. 609 original microphotographs of vessels, numerical data from experts’ measurements, and microphotographs with outlines of these measurements for each of the vessels are presented. The presented database will be useful for the development of new software solutions for the analysis of histological micrograph.

NPO

The dataset is recorded with an on-vehicle ZED stereo camera in both urban and rural environments The dataset contains various lighting conditions, such as normal lights, large-area shadows, dim lights, and sun glare. There are also different weather conditions, such as sunny, cloudy, and snowy. Negative obstacles (i.e., potholes and cracks) and positive obstacles (i.e., pedestrians, cars, and motorcycles) in 5, 000 images are labelled

NYUDv2-IS

A RGB-D dataset converted from NYUDv2 into COCO-style instance segmentation format. To construct NYUDv2-IS, specifically tailored for instance segmentation, we generated instance masks that delineate individual objects in each image. These masks were labeled using the object class annotations provided in the original NYUDv2 dataset, which is distributed in MATLAB format. The process involved several key steps: (1) extracting binary instance masks, (2) converting these masks into polygon representations, and (3) generating COCO-style annotations. Each annotation includes essential attributes such as category ID, segmentation masks, bounding boxes, object areas, and image metadata. During this conversion, we focused on 9 categories out of the original 13 classes, excluding non-instance categories such as walls and floors. To ensure dataset quality, images without any object annotations were systematically removed.

S-BIAD843

Late third instar wing imaginal discs were cultured in Shields and Sang M3 media (Sigma) supplemented with 2% FBS (Sigma), 1% pen/strep (Gibco), 3ng/ml ecdysone (Sigma) and 2ng/ml insulin (Sigma). Wing discs were cultured in 35mm fluorodishes (WPI) under 12mm filters (Millicell), as described in https://doi.org/10.1038%2Fs41567-019-0618-1 Segmentation label of individual cells of Drosophila wing disc curated by experts from a model prediction with cellpose.

SimGas

This dataset consists of computer-generated images for gas leakage segmentation. It features diverse backgrounds, interfering foreground objects, and precise ground truth annotations.

SUN-RGBD-IS

A RGB-D dataset converted from SUN-RGBD into COCO-style instance segmentation format. To transform SUN-RGBD into an instance segmentation benchmark (i.e., SUN-RGBDIS), we employed a pipeline similar to that of NYUDv2-IS. We selected 17 categories from the original 37 classes, carefully omitting non-instance categories like ceilings and walls. Images lacking any identifiable object instances were filtered out to maintain dataset relevance for instance segmentation tasks. We systematically convert segmentation annotations into COCO format, generating precise bounding boxes, instance masks, and object attributes.

Aachen-Heerlen Annotated Steel Microstructure Dataset

​The Aachen-Heerlen annotated steel microstructure dataset comprises 1,705 scanning electron microscopy (SEM) images of bainitic steel samples. Each image is annotated with expert-delineated polygons highlighting martensite-austenite (MA) islands—complex blocky structures that significantly influence the mechanical properties of steel. Additionally, the dataset includes metadata detailing the chemical composition, transformation temperatures, and cooling rates of the steel samples.​ Motivation and Summary of Content The primary motivation for creating this dataset is to facilitate the development of machine learning models capable of automatically and accurately detecting MA islands in steel microstructures. Manual identification of these structures is labor-intensive and prone to subjectivity. By providing a comprehensive set of annotated images, the dataset aims to enhance reproducibility and efficiency in microstructural analysis within materials science.​ Potential Use Cases Materials Science Research: Researchers can utilize this dataset to explore the relationship between the morphology of MA islands and the mechanical characteristics of bainitic steel, potentially leading to improved material design and processing techniques.​ Computer Vision Applications: The dataset serves as a valuable resource for training and evaluating object segmentation models, particularly in recognizing and delineating complex geometries like MA islands. This can advance the development of machine learning algorithms tailored for materials characterization.​ Quality Control in Steel Manufacturing: Automated detection and analysis of MA islands can be integrated into quality control processes, enabling more consistent and objective assessments of steel microstructures during production.​ By bridging the gap between materials science and machine learning, this dataset fosters interdisciplinary approaches to understanding and optimizing steel microstructures.​ Source: https://www.nature.com/articles/s41597-021-00926-7

PALMS

Data in this study come from western Ecuador's Choco tropical forest, including \textit{Fundación para la Conservación de los Andes Tropicales Reserve and adjacent Reserva Ecológica Mache-Chindul park} (FCAT; 00$^\circ$23'28'' N, 79$^\circ$41'05'' W), \textit{Jama-Coaque Ecological Reserve} (00$^\circ$06'57'' S, 80$^\circ$07'29'' W), \textit{Canande Reserve} (0$^\circ$31'34'' N 79$^\circ$12'47'' W), and \textit{Tesoro Escondido Reserve} (0$^\circ$33'16'' N 79$^\circ$10'31'' W). FCAT is a high diversity humid tropical forest at elevation $\sim$500m, receiving $\sim$3000 mm yr$^{-1}$ precipitation with persistent fog during drier period. Jama-Coaque ranges from the boundary of the tropical moist deciduous/tropical moist evergreen forest at the lower elevations ($\sim$1000 mm precipitation yr$^{-1}$, $\sim$250 m asl) to fog-inundated wet evergreen forests above 580m to 800m. Canande (350–500 m elevation) and Tesoro Escondido ($\sim$200 m elevation) are lowland everwet Choco forests, both receiving 4000–5000 mm yr$^{-1}$ precipitation with no month experiencing drought stress or precipitation below 100 mm. These forests host several palm species with exposed canopy crowns, including the economically important \textit{Iriartea deltoidea}, \textit{Socratea exorrhiza}, and \textit{Oenocarpus bataua}, with lesser amounts of \textit{Attalea colenda} and \textit{Astrocaryum standleyanum}, and species composition varying across study sites

Tornet

The Tornado Network (TorNet) dataset is a large, high-resolution benchmark dataset developed to support machine learning research in tornado detection and prediction. It comprises over 200,000 radar samples derived from 9 years of full-resolution, polarimetric WSR-88D (NEXRAD) level-II and level-III radar data. Each sample, called a "chip," includes multiple radar variables—such as reflectivity, radial velocity, spectrum width, differential reflectivity, correlation coefficient, and specific differential phase—captured across two elevation angles and four time steps spaced five minutes apart. Rather than converting radar data to Cartesian coordinates, TorNet retains its native polar format, preserving spatial fidelity near the radar site. This level of detail enables the dataset to support a wide range of machine learning techniques, including deep learning models that can learn directly from raw radar imagery.

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.