Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
161
datasets available to search
ShareScore release 0.9.0
Dataset results
161 results for “unsupervised”
ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation
<p>There has been a recent surge in methods that aim to decompose and segment scenes into multiple objects in an unsupervised manner, i.e., unsupervised multi-object segmentation. Performing such a task is a long-standing goal of computer vision, offering to unlock object-level reasoning without requiring dense annotations to train segmentation models. Despite significant progress, current models are developed and trained on visually simple scenes depicting mono-colored objects on plain backgrounds. The natural world, however, is visually complex with confounding aspects such as diverse textures and complicated lighting effects. In this study, we present a new benchmark called ClevrTex, designed as the next challenge to compare, evaluate and analyze algorithms. ClevrTex features synthetic scenes with diverse shapes, textures and photo-mapped materials, created using physically based rendering techniques. ClevrTex has 50k examples depicting 3-10 objects arranged on a background, created using a catalog of 60 materials, and a further test set featuring 10k images created using 25 different materials. We benchmark a large set of recent unsupervised multi-object segmentation models on ClevrTex and find all state-of-the-art approaches fail to learn good representations in the textured setting, despite impressive performance on simpler data. We also create variants of the ClevrTex dataset, controlling for different aspects of scene complexity, and probe current approaches for individual shortcomings.</p> <p>Project webpage: https://www.robots.ox.ac.uk/~vgg/data/clevrtex/</p> <p>These are <strong>the variant datasets</strong>. Please see project page for links to the main dataset.</p>
ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation
<p>There has been a recent surge in methods that aim to decompose and segment scenes into multiple objects in an unsupervised manner, i.e., unsupervised multi-object segmentation. Performing such a task is a long-standing goal of computer vision, offering to unlock object-level reasoning without requiring dense annotations to train segmentation models. Despite significant progress, current models are developed and trained on visually simple scenes depicting mono-colored objects on plain backgrounds. The natural world, however, is visually complex with confounding aspects such as diverse textures and complicated lighting effects. In this study, we present a new benchmark called ClevrTex, designed as the next challenge to compare, evaluate and analyze algorithms. ClevrTex features synthetic scenes with diverse shapes, textures and photo-mapped materials, created using physically based rendering techniques. ClevrTex has 50k examples depicting 3-10 objects arranged on a background, created using a catalog of 60 materials, and a further test set featuring 10k images created using 25 different materials. We benchmark a large set of recent unsupervised multi-object segmentation models on ClevrTex and find all state-of-the-art approaches fail to learn good representations in the textured setting, despite impressive performance on simpler data. We also create variants of the ClevrTex dataset, controlling for different aspects of scene complexity, and probe current approaches for individual shortcomings.</p> <p>Project webpage: https://www.robots.ox.ac.uk/~vgg/data/clevrtex/</p> <p>This is the <strong>main dataset and OOD test set. </strong>Please see project page for links to the dataset variants.</p>
An Empirical Evaluation of Unsupervised Event Log Abstraction Techniques in Process Mining
<p>This upload contains the event logs, generated by L-Sim, on which the experiments of the related paper were performed.</p><p>The related paper is accepted in the journal Information Systems.</p>
Data for the analysis of aquifer-system deformation in the Doñana Natural Space (Spain) using unsupervised cloud-computed InSAR data and wavelet analysis
<p>This are the data necessary to correlate InSAR and hydrogeological information through wavelet analysis, by WaSAR Python script (Jiménez-González & Guardiola-Albert, 2022, http://doi.org/10.5281/zenodo.6334996). The structure and information about the data is the following:</p> <p>PSBAS: Processed Interferometric Synthetic Aperture Radar (InSAR) data from the European Space Agency (ESA) Sentinel-1 satellites to estimate line-of-sight (LOS) ground motion in the period 2014-2020 in the Doñana area (SW Spain). These images have been processed using the P-SBAS approach (Parallel Small BAseline Subset), which is the parallel computing solution for the SBAS processing chain at the ESA Geohazards Exploitation Platform (GEP) by CNR-IREA.</p> <p>Aggregates deformation: Former InSAR information aggregated in polygons</p> <p>Climate: rainfall and ET information in the Doñana area for the 2014-2020 period. Daily records of evapotranspiration and precipitation have been obtained from the agroclimatic stations belonging to the Junta de Andalucía (https://www.juntadeandalucia.es/agriculturaypesca/ifapa/riaweb/web/).</p> <p>Piezometry: piezometry information in Doñana area for the 2014-2020 period. Groundwater level information was provided by the piezometric networks of the Guadalquivir Hydrographic Confederation and the Geological and Mining Institute of Spain.</p> <p>Pump rates: estimated pumping rate time series in the Matalascañas touristic resort</p>
BRAIN Journal-Performance Analysis of Unsupervised Clustering Methods for Brain Tumor Segmentation-Figure 4.Performance based on no. of tumor pixel & execution time
<p>In this paper we segmented the brain tumors in axial view of MR images with the help of<br> unsupervised clustering method i.e. K-means clustering. The unsupervised clustering methods gave<br> the better results than traditional method.<br> The performance analysis and comparison is done f on the basis of no. of tumor pixels in<br> segmented brain tumor and the execution time for the same. Regarding the no. of tumor pixels, Kmeans<br> clustering gave a better result than the other methods. The clustering algorithms were tested<br> with a data base of 20 MRI brain images. K-means clustering achieved almost 90%result</p>
BRAIN Journal-Performance Analysis of Unsupervised Clustering Methods for Brain Tumor Segmentation-Figure 3:(a) Input MR Image (b) Enhanced Image (c) Segmented Tumor (d) Located brain tumor
<p>Figure 3 shows three different original brain MR images, contrast enhancement of the<br> images, segmented images using K-means algorithm and finally located tumor. Fig 1.4 shows the<br> performance of the unsupervised clustering methods with the no. of tumor pixels and execution<br> time to locate the brain tumor.</p>
BRAIN Journal-Performance Analysis of Unsupervised Clustering Methods for Brain Tumor Segmentation-Figure 2. Stages of software implementation
<p>The algorithm has two stages, first is pre-processing of given MRI image and after that<br> segmentation and then perform morphological operations.</p>
BRAIN Journal-Performance Analysis of Unsupervised Clustering Methods for Brain Tumor Segmentation-Figure 1. Diagnosis Rate in different Countrie
<p>In MRI images, the amount of data is too much for manual segmentation. The procedure is<br> tedious, time, labor consuming, subjective and requires expertise. This gave way to methods that are<br> computer-aided with user interaction at varying levels. These methods are automatic and objective<br> and the results are highly reproducible. We designed software tool for locating brain tumor, based<br> on unsupervised clustering methods and analyzed its performance</p>
SPUSPO: Spatially Partitioned Unsupervised Segmentation Parameter Optimization for Efficiently Segmenting Large Heterogeneous Areas
<p>This dataset contains several data, results and processing material from the application of GEOBIA-based, Spatially Partitioned Segmentation Parameter Optimization (SPUSPO) in the city of Ouagadougou. In detail in contains:</p> <ul> <li><strong>A Land Use - Land Cover map of Ouagadougou derived through SPUSPO. The classifier used was Extreme Gradient Boosting (XGBoost). </strong> <p>Labels :</p> <p>2 : Artificial Ground Surface</p> <p>0 : Building</p> <p>5 : Low Vegetation</p> <p>4 : Tree</p> <p>1 : Swimming Pool</p> <p>3 : Bare Ground</p> <p>7 : Shadow</p> <p>6 : Inland Water</p> </li> </ul> <p> </p> <ul> <li><strong>The training and test data used in the study (SPUSPO and benchmark approach). </strong></li> </ul> <p>The data are given in a csv format.</p> <ul> <li><strong>The Jupyter notebook code which involves Python and GRASS GIS to automatize and efficiently perform SPUSPO in a large dataset.</strong></li> </ul> <p>Python code calling GRASS GIS functions for automatizing the procedure.</p> <p> </p> <ul> <li><strong>The segmentation layers coming from SPUSPO and the benchmark approaches (in raster formats due to data limitations).</strong></li> </ul> <p>Segmentation rasters for each approach.</p> <ul> <li><strong>The R code for optimization of XGBoost as well as feature selection with VSURF and classification of the whole dataset.</strong></li> </ul> <p> </p> <ul> <li><strong>Segmentation evaluation metrics.</strong></li> </ul> <p>A csv file with the data sued to compute the Area Fit Index for each approach.</p> <ul> <li><strong>Morphological zones of Ouagadougou as created by Grippa et al. 2017 a shp format.</strong></li> </ul>
UNSUPERVISED MACHINE LEARNING AND VECTOR MODELS IN DESIGNING AND OPTIMIZATION OF TELECOM RETAIL CHANNELS
<p>This paper examines the use of unsupervised machine learning and vector models in the design and optimization of retail channels for telecommunications services. Unsupervised machine learning allows you to analyze and identify hidden patterns in large volumes of untagged data, which is especially important in a dynamically changing consumer market. Vector models, in turn, provide high accuracy of demand forecasting and inventory management, contributing to an increase in the efficiency of trading channels. The synergy of these technologies allows companies to improve customer experience, optimize operational processes and increase competitiveness in the market. The main focus of the work is on data processing methods, including correlation analysis, the use of the support vector machine (SVM) method and its adaptation to solve problems related to predicting customer behavior and optimizing logistics processes.</p>
Relations from Italian Wikipedia using Unsupervised Information Extraction
<p>This dataset contains relations extracted from the Italian Wikipedia by the WikiOIE framework.<br> WikiOIE is based on UDPipe and the Universal Dependencies project for text processing.<br> It easily allows customizing the information extraction (IE) approach to automatically extract triples (subject, predicate, object).<br> This dataset contains relations extracted by two unsupervised IE methods. The former (<strong>simple</strong>) is based only on PoS-tag patterns; the latter (<strong>simpledep</strong>) also uses syntactic dependencies. <br> The extraction process is provided in JSON format.</p> <p>More information and the Java code are available here https://github.com/pippokill/WikiOIE</p> <p>Pierluigi Cassotti, Lucia Siciliani, Pierpaolo Basile,Marco de Gemmis, and Pasquale Lops. 2021. Extracting relations from Italian Wikipedia using unsupervised information extraction. In Proceedings of the 11th Italian Information Retrieval Workshop 2021 (IIR 2021). CEUR-WS.</p>
Learning Unsupervised Hierarchies of Audio Concepts
<p>Dataset of our paper <a href="https://arxiv.org/abs/2207.11231">"Learning Unsupervised Hierarchies of Audio Concepts"</a> published at the <a href="https://ismir2022.ismir.net/">ISMIR 2022</a> conference.</p> <p>For usage examples, please refer to our code repository at <a href="https://github.com/deezer/concept_hierarchy">github.com/deezer/concept_hierarchy</a>.</p> <p><strong>Paper abstract</strong></p> <p>Music signals are difficult to interpret from their low-level features, perhaps even more than images: e.g. highlighting part of a spectrogram or an image is often insufficient to convey high-level ideas that are genuinely relevant to humans. In computer vision, concept learning was therein proposed to adjust explanations to the right abstraction level (e.g. detect clinical concepts from radiographs). These methods have yet to be used for MIR.<br> In this paper, we adapt concept learning to the realm of music, with its particularities. For instance, music concepts are typically non-independent and of mixed nature (e.g. genre, instruments, mood), unlike previous work that assumed disentangled concepts. We propose a method to learn numerous music concepts from audio and then automatically hierarchise them to expose their mutual relationships. We conduct experiments on datasets of playlists from a music streaming service, serving as a few annotated examples for diverse concepts. Evaluations show that the mined hierarchies are aligned with both ground-truth hierarchies of concepts -- when available -- and with proxy sources of concept similarity in the general case.</p> <p><strong>Citation</strong></p> <p>If you use this material, please consider citing our work with the following:</p> <pre><code>@inproceedings{afchar2022learning, title={Learning Unsupervised Hierarchies of Audio Concepts}, author={Afchar, Darius and Hennequin, Romain and Guigue, Vincent}, booktitle={International Society of Music Information Retrieval Conference (ISMIR)}, year={2022} }</code></pre> <p><strong>How can I send you a love letter?</strong></p> <p>You can contact us at <a href="mailto:research@deezer.com?subject=Dataset%20ISMIR%20Afchar">research@deezer.com</a>.</p>
Data and scripts from "Unsupervised learning for structure detection in plastically deformed crystals"
<p>This documents contains the scripts and dataset used for the paper "Unsupervised learning for structure detection in plastically deformed crystals".</p> <p> </p> <p>More precisely it contains 4 folders :</p> <p><br> DumpForFigures : subfolder containing the atomic positions in .dump format (see lammps documentation) used for the article figures.</p> <p>DumpForTraining : subfolder containing the atomic position in .dump format (see lammps documentation) used for training the autoencoder.</p> <p>ScriptsToDetectStructuresFromDump : subfolder containing the script sused to detect the substructures of the system by combining autoencoder and clustering methods. This folder contains a readme with the details of the contents.</p> <p>ScriptToGenerateDump : subfolder containing the scripts used to generate the atomic data with molecular dynamics. These data are then used to train the autoencoder. This folder contains a readme with the details of the contents.</p> <p>REQUIREMENTS :</p> <p> </p> <p>Lammps</p> <p>Python3 with packages :</p> <p>-numpy</p> <p>-matplotlib</p> <p>-pyscal</p> <p>-sci-kit learn</p> <p>-pytorch</p> <p>-glob</p> <p> </p> <p> </p> <p> </p>
Dataset for Unsupervised Clustering of CFG Files
<p>This dataset consists of control flow graphs (CFGs) of malware and benign binary files. Due to the security risk of sharing malware binary files online, these binary files are not shared. However, the hash values of the binaries are given for information.</p> <p>The dataset is associated with the software available at https://github.com/MSUSEL/unsupervised-graph (link may change). A manuscript outlining the problem and software solution, titled "Malware Detection Using Unsupervised Clustering of Binary File Control Flow Graphs," is under review for publication in IEEE Transactions on Information Forensics and Security. Upon publication, the related identifiers for both the code and the paper will be updated.</p>
Unsupervised neural network for single cell Multi-omics INTegration (UMINT): An application to health and disease
<p>This dataset repository corresponds to the project Unsupervised neural network for single cell Multi-omics INTegration (UMINT): An application to health and disease.</p>
Quasar Factor Analysis – An Unsupervised and Probabilistic Quasar Continuum Prediction Algorithm with Latent Factor Analysis
<p>Dataset used in <em>Quasar Factor Analysis – An Unsupervised and Probabilistic Quasar Continuum Prediction Algorithm with Latent Factor Analysis </em>[<a href="https://arxiv.org/abs/2211.11784">arXiv: <strong>2211.11784</strong></a>]. This dataset will be helpful to validate different continuum prediction model and study absorption systems.<br> <br> The descriptions of individual files can be found here:</p> <ul> <li><a href="/api/files/01c3b414-7572-4a24-9c67-fbab6ae05969/sdss-dr16.tar.gz?versionId=427c1aca-6f12-4e84-b91e-f9a3d678329e">sdss-dr16.tar.gz</a> : continuum prediction for ~100,000 quasar spectra from SDSS DR16, see Section 3.1 in <a href="https://arxiv.org/abs/2211.11784">arXiv:211.11784</a>;</li> <li><a href="https://zenodo.org/api/files/01c3b414-7572-4a24-9c67-fbab6ae05969/sdss-mock-with-dla-with-perturb.tar.gz?versionId=55bc466d-4cbf-43ba-9b83-209ffba4ec30">sdss-mock-with-dla-with-perturb.tar.gz </a> : ~150,000 mock quasar spectra to validate QFA performance with perturbation on quasar continuum from PCA template, see Section 3.2 in <a href="https://arxiv.org/abs/2211.11784">arXiv:211.11784</a>;</li> <li><a href="https://zenodo.org/api/files/01c3b414-7572-4a24-9c67-fbab6ae05969/sdss-mock-with-dla-without-perturb.tar.gz?versionId=efa5d05a-2a40-4a43-801e-c95b29a4efb2">sdss-mock-with-dla-without-perturb.tar.gz</a>: ~150,000 mock quasar spectra to validate QFA performance with quasar continuum directly from PCA template, see Section 3.2 in <a href="https://arxiv.org/abs/2211.11784">arXiv:211.11784</a>.<br> <br> <br> </li> </ul>
Dataset Artifact for Prodigy: Towards Unsupervised Anomaly Detection in Production HPC Systems
<p>The dataset contains a small set of application runs from Eclipse supercomputer. The applications run with and without synthetic HPC performance anomalies. More detailed information regarding synthetic anomalies can be found at: https://github.com/peaclab/HPAS.</p> <p>We have chosen four applications, namely LAMMPS, sw4, sw4Lite, and ExaMiniMD, to encompass both real and proxy applications. We have executed each application five times on four compute nodes without introducing any anomalies. To showcase our experiment, we have specifically selected the "memleak" anomaly as it is one of the most commonly occurring types. Additionally, we have also executed each application five times with the chosen anomaly. The dataset we have collected consists of a total of 160 samples, with 80 samples labeled as anomalous and 80 samples labeled as healthy. For the details of applications please refer to the paper.</p> <p>The applications were run on Eclipse, which is situated at Sandia National Laboratories. Eclipse comprises 1488 compute nodes, each equipped with 128GB of memory and two sockets. Each socket contains 18 E5-2695 v4 CPU cores with 2-way hyperthreading, providing substantial computational power for scientific and engineering applications.</p>
Materials for the "Unsupervised classification (clustering) of satellite images" workshop
<p>Dataset for the "<strong>Unsupervised classification (clustering) of satellite images</strong>" workshop on <a href="https://opengeohub.org/summer-school/opengeohub-summer-school-poznan-2023/">OpenGeoHub Summer School 2023</a>. The repository with the code can be found on GitHub: <a href="https://github.com/kadyb/OGH2023">https://github.com/kadyb/OGH2023</a>.</p> <p>In the .zip archive there are two catalogs: "<em>data</em>" and "<em>task</em>", which include:</p> <ul> <li>Landsat 8 scene (7 spectral bands) + metadata;</li> <li>polygons with coverage of Poznań and Szamotuły counties.</li> </ul> <p>The satellite data was downloaded from <a href="https://earthexplorer.usgs.gov/">EarthExplorer</a>.</p>
Unsupervised microscopy image registration datasets
<p>This repository contains the raw microscopy datasets for the article entitled "<strong>Unsupervised multimodal image registration with deep learning for biomedical microscopy".</strong></p> <p> </p>
Dataset of UAI 2021 Paper "An Unsupervised Video Game Playstyle Metric via State Discretization"
<p>This is a part of dataset of the paper published in UAI 2021 (37th Conference on Uncertainty in Artificial Intelligence).</p> <p>Including training datasets, testing datasets, and HSD models of three game platforms used in the paper: TORCS, RGSK, and Atari.</p> <p>The example program for using this file will be put on the author's github repo branch: <a href="https://github.com/DSobscure/cgi_drl_platform/tree/playstyle_uai2021">https://github.com/DSobscure/cgi_drl_platform/tree/playstyle_uai2021</a></p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.