Papers with Code 아카이브

Instance Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
17
평가표
36
보존된 평가 기록
338

Instance Segmentation is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.

Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21

데이터셋

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

UAVBillboards

Mapping urban large-area advertising structures using drone imagery and deep learning-based spatial data analysis. The dataset contains 1361 images supplemented with additional spatial metadata, together with 5210 annotations in a COCO-like format.

UFBA-425

We introduce a set of 425 panoramic X-rays with Human annotated Bounding Boxes and Polygons, the 425 images are a subset of UFBA-UESC Dental Dataset. This dataset can be extensively used for detection and segmentation tasks for Dental Panoramic X-rays. Refer to Description for understanding the organisation of annotations and panoramic X-rays. The dataset contains distribution of panoramic X-rays across ten different categories.

UMD-i Affrodance Dataset

One-Shot Affordance Part Segmentation variant of the UMD dataset. Each object instance in the dataset contains a single image.

VizWiz-FewShot

VizWiz-FewShot is a a few-shot localization dataset originating from photographers who authentically were trying to learn about the visual content in the images they took. It includes nearly 10,000 segmentations of 100 categories in over 4,500 images that were taken by people with visual impairments.

XA Bin-Picking

XA Bin-Picking is a point-cloud dataset comprising both simulated and real-world scenes with three industrial parts. Synthesized scenes consists of 1000 training samples. The test samples are real scenes and the ground truth instance labels are made manually. There are 20 to 30 identical types of parts randomly piled up in a scene. Each scene contains about 60,000 boundary points. Each point in the scene has instance annotations. The parts are texture-less and have no discernible color. Both of training samples and test sam- ples only contain the boundary points of parts. Source: A Convolutional Neural Network for Point Cloud Instance Segmentation in Cluttered Scene Trained by Synthetic Data Without Color Image Source: A Convolutional Neural Network for Point Cloud Instance Segmentation in Cluttered Scene Trained by Synthetic Data Without Color

YIM Dataset

An instance segmentation dataset of yeast cells in microstructures. The dataset includes 493 densely annotated microscopy images. For more information see the paper "An Instance Segmentation Dataset of Yeast Cells in Microstructures".

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

CornHub

🌽 CornHub: Instance-Segmentation Dataset of Corn Cobs Version: 1.0.0 Date: 2025-05-18 License: CC BY 4.0 Author: Sebastian Borukało ## 📦 Description CornHub is an instance-segmentation dataset of corn cobs in real field conditions. It contains 304 high-resolution RGB images in three variants: - FULL (2432×2432 px) - LITE (1024×1024 px) - ULTRALITE (512×512 px) Captured at varying distances (close-up and wide-angle), lighting conditions (sunny, overcast), and viewpoints, each corn cob is annotated as its own grayscale mask (single channel): - 0 = background - 1, 2, 3… = individual corn cob instances Images and masks are provided in PNG format. Use CornHub to train and evaluate instance-segmentation models in agriculture, field robotics, and computer vision research. ### DataSet view: | Version | Filename | Resolution | |------------------|:-------------------------:|:----------------:| | Full | CornHub_FULL_2432.zip | 2432×2432 px | | Lite | CornHub_LITE_1024.zip | 1024×1024 px | | Ultra-Lite | CornHub_ULTRALITE_512.zip | 512×512 px | ## 📂 Download Options Available on: - Kaggle - Zenodo - Papers With Code ## 🤝 Credits This dataset is free to use and you can use it in any project or paper, however I would be glad if you would cite me and give credit - as it is stated in the license. CornHub: Instance-Segmentation Dataset of Corn Cobs Author: Sebastian Borukało DOI: https://doi.org/10.5281/zenodo.15453713 DOI: 10.5281/zenodo.15453713

InfiniteRep

InfiniteRep is a synthetic, open-source dataset for fitness and physical therapy (PT) applications. It includes 1k videos of diverse avatars performing multiple repetitions of common exercises. It includes significant variation in the environment, lighting conditions, avatar demographics, and movement trajectories. From cadence to kinematic trajectory, each rep is done slightly differently -- just like real humans. InfiniteRep videos are accompanied by a rich set of pixel-perfect labels and annotations, including frame-specific repetition counts. The dataset features: + 100 videos per exercise, spanning 5 to 10 repetitions each (1,000 videos total) + 7 unique indoor scenes + Realistic environmental occlusion (+ corresponding labels) + Diverse lighting conditions + Varied body shape, skin tones, and clothing + Rich annotations for 2D and 3D supervision ## Exercises The dataset currently includes the following exercises: + Pushups + Alternating Bicep Curls (with dumbbells) + Delt Flys (with dumbbells) + Squats + Bird Dogs + Supermans + Bicycle Crunches + Leg Raises + Front Raises (with dumbbells) + Overhead Press (with dumbbells) ## Annotations The dataset includes the following annotations: + Bounding boxes + Segmentation masks + Keypoints + Joint angles (quaternions) + Percent occlusion + Avatar characteristics + Camera position + and more Want depth labels? They are not included in the dataset but we can send them to you. Email us at info@toinfinity.ai. ## Download Download the dataset: toinfinity.ai/infiniterep Github repo with additional documentation: https://github.com/toinfinityai/InfiniteRep ## Need more data? Infinity AI specializes in generating custom synthetic data. If you need more (or different data), drop us a line at info@toinfinity.ai (we read every email).

InLUT3D

This dataset called Indoor Lodz University of Technology Point Cloud Dataset (InLUT3D) is a point cloud set tailored for real object classification and both semantic and instance segmentation tasks. Comprising of 321 scans, some areas in the dataset are covered by multiple scans. All of them are captured using the Leica BLK360 scanner. The points are divided into 18 distinct categories outlined in the label.yaml file along with their respective codes and colors. Among categories you will find: - ceiling, - floor, - wall, - stairs, - column, - chair, - sofa, - table, - storage, - door, - window, - plant, - dish, - wallmounted, - device, - radiator, - lighting, - other. Several challenges are intrinsic to the presented dataset: 1. Extremely non-uniform categories distribution across the dataset. 1. Presence of virtual images, particularly in reflective surfaces, and data exterior to windows and doors. 1. Occurrence of missing data due to scanning shadows (certain areas were inaccessible to the scanner's laser beam). 1. High point density throughout the dataset. Each PTS file contains 8 columns: | Column ID | Description | |---------------|-------------------------------------------------| | 1 | X Cartesian coordinate | | 2 | Y Cartesian coordinate | | 3 | Z Cartesian Coordinate | | 4 | Red colour in RGB space in the range [0, 255] | | 5 | Green colour in RGB space in the range [0, 255] | | 6 | Blue colour in RGB space in the range [0, 255] | | 7 | Category code | | 8 | Instance ID |

Multi-Spectral Leaf Segmentation

This dataset were acquired with the Airphen (Hyphen, Avignon, France) six-band multi-spectral camera configured using the 450/570/675/710/730/850 nm bands with a 10 nm FWHM. And acquired on the site of INRAe in Montoldre (Allier, France, at 46°20'30.3"N 3°26'03.6"E) within the framework of the “RoSE challenge” founded by the French National Research Agency (ANR). Images contains bean, with various natural weeds (yarrows, amaranth, geranium, plantago, etc) and sowed ones (mustards, goosefoots, mayweed and ryegrass) with very distinct characteristics in terms of illumination (shadow, morning, evening, full sun, cloudy, rain, ...) The ground truth is defined for each images with polygons around leafs boundaries: In addition, each polygons are labeled into crop or weed. (2020-06-11)

ShipRSImageNet

ShipRSImageNet is a large-scale fine-grainted dataset for ship detection in high-resolution optical remote sensing images. The dataset contains 3,435 images from various sensors, satellite platforms, locations, and seasons. Each image is around 930×930 pixels and contains ships with different scales, orientations, and aspect ratios. The images are annotated by experts in satellite image interpretation, categorized into 50 object categories images. The fully annotated ShipRSImageNet contains 17,573 ship instances. There are five critical contributions of the proposed ShipRSImageNet dataset compared with other existing remote sensing image datasets. Images are collected from various remote sensors cover- ing multiple ports worldwide and have large variations in size, spatial resolution, image quality, orientation, and environment. Ships are hierarchically classified into four levels and 50 ship categories. The number of images, ship instances, and ship cate- gories is larger than that in other publicly available ship datasets. Besides, the number is still increasing. We simultaneously use both horizontal and oriented bounding boxes, and polygons to annotate images, providing detailed information about direction, background, sea environment, and location of targets. We have benchmarked several state-of-the-art object detection algorithms on ShipRSImageNet, which can be used as a baseline for future ship detection methods.

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