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.
328
datasets available to search
ShareScore release 0.9.0
Dataset results
328 results for “segmentation dataset”
Indian Brain Segmentation Dataset(IBSD)
<p>Segmentation of sub-cortical structures from MRI scans is of interest in many neurological diagnoses. Indian Brain Segmentation Dataset (IBSD) consists of high-quality 1.5T T1w MRI data of 114 subjects generated under fixed imaging protocol along with corresponding manual annotation data of 14 sub-cortical structures done by expert radiologists. The number of MR scans in the dataset consists of an approximately equal number of male and female subjects belonging to a young age group (20-30 years). This data has been used to create a template for the young Indian population [<a href="https://www.neurologyindia.com/article.asp?issn=0028-3886;year=2019;volume=67;issue=1;spage=229;epage=234;aulast=Sivaswamy">1</a>]. This dataset can also be utilized for variety of tasks such as segmenting structures of interest, aligning/ registering images, etc, using traditional methods as well as Deep Learning approaches since it has adequate quantity of high quality data.</p>
Dataset from "Identifying zebrafish segmentation phenotype features using multiple instance learning"
<p>The dataset was used to produce the results from the "Identifying zebrafish segmentation phenotype features using multiple instance learning" manuscript. It contains images of zebrafish embryos obtained by in situ hybridization that were used to train and evaluate the performance of different neural network-based image classifiers. Images were split into 4 classes: unmodified (WT) zebrafish embryo, and 3 more phenotypes reflecting different segmentation clock defects.<br> Folder 'data' contains 3 different directories: 'training', the set used for training of the classifiers, 'validation', the set used for evaluation of the performance of the classifiers, with 20 images from each class, and 'fish_part_labels' that contains the annotation of zebrafish embryo parts (head, trunk, tail, yolk, and yolk extension) of the images from the 'validation' set.</p>
Shifts Multiple Sclerosis Lesion Segmentation Dataset Part 1
<p>This archive contains the part 1 of Shift Benchmark on Multiple Sclerosis lesion segmentation data. This dataset is provided by the Shifts Project to enable assessment of the robustness of models to distributional shift and the quality of their uncertainty estimates. This part is the MSSEG data collected in the digital repository of the OFSEP Cohort provided in the context of the MICCAI 2016 and 2021 challenges. A full description of the benchmark is available in https://arxiv.org/pdf/2206.15407. Part 2 of the data is available <a href="https://zenodo.org/record/7051692">here</a>. To find out more about the Shifts Project, please visit https://shifts.ai .</p>
MatSeg: Material State Segmentation Dataset and Benchmark
<p><strong>MatSeg Dataset and benchmark for zero-shot material state segmentation.</strong></p> <p><em>MatSeg Benchmark </em>containing 1220 real-world images and their annotations is available at <strong>MatSeg_Benchmark.zip </strong> the file contains documentation and Python readers.</p> <p><em>MatSeg dataset<strong> </strong></em>containing synthetic images with infused natural images patterns is available at <strong>MatSeg3D_part_*.zip</strong> and <strong>MatSeg3D_part_*.zip<em> </em></strong>(* stand for number).</p> <p><strong>MatSeg3D_part_*.zip: </strong>contain synthethc 3D scenes</p> <p><strong>MatSeg2D_part_*.zip:</strong> contain syntethc 2D scenes</p> <p><em>Readers and documentation<strong> </strong></em>for the synthetic data are available at:<strong> Dataset_Documentation_And_Readers.zip</strong></p> <p><em>Readers and documentation</em> for the real-images benchmark are available at:<strong> MatSeg_Benchmark.zip<br><br>The Code used to generate the MatSeg Dataset is available at: <a href="../records/11401072">https://zenodo.org/records/11401072</a></strong></p> <p><strong>Additional permanent sources for downloading the dataset and metadata:<a href="https://e.pcloud.link/publink/show?code=kZxsXTZIk88l74Jb3YeMeOcjOlJJVIqvHj7"> 1</a>,<a href="https://icedrive.net/s/XxgZSif7NgYRbjvDN5w9aiWZ1fR3"> 2</a></strong></p> <p><strong>Evaluation scripts for the Benchmark are now available at:</strong></p> <p><a href="../records/13402003"><strong>https://zenodo.org/records/13402003</strong></a> and <a href="https://e.pcloud.link/publink/show?code=XZsP8PZbT7AJzG98tV1gnVoEsxKRbBl8awX">https://e.pcloud.link/publink/show?code=XZsP8PZbT7AJzG98tV1gnVoEsxKRbBl8awX</a></p> <div> <h2> </h2> <h2>Description</h2> <p>Materials and their states form a vast array of patterns and textures that define the physical and visual world. Minerals in rocks, sediment in soil, dust on surfaces, infection on leaves, stains on fruits, and foam in liquids are some of these almost infinite numbers of states and patterns. </p> <p>Image segmentation of materials and their states is fundamental to the understanding of the world and is essential for a wide range of tasks, from cooking and cleaning to construction, agriculture, and chemistry laboratory work.</p> <p>The MatSeg dataset focuses on zero-shot segmentation of materials and their states, meaning identifying the region of an image belonging to a specific material type of state, without previous knowledge or training of the material type, states, or environment. </p> <p>The dataset contains a large set of (100k) synthetic images and benchmarks of 1220 real-world images for testing.</p> <h2>Benchmark</h2> <p>The benchmark contains 1220 real-world images with a wide range of material states and settings. For example: food states (cooked/burned..), plants (infected/dry.) to rocks/soil (minerals/sediment), construction/metals (rusted, worn), liquids (foam/sediment), and many other states in without being limited to a set of classes or environment. The goal is to evaluate the segmentation of material materials without knowledge or pretraining on the material or setting. The focus is on materials with complex scattered boundaries, and gradual transition (like the level of wetness of the surface).</p> <p>Evaluation scripts for the Benchmark are now available at: <a href="../records/13402003"><strong>1</strong></a> and <a href="https://e.pcloud.link/publink/show?code=XZsP8PZbT7AJzG98tV1gnVoEsxKRbBl8awX">2.</a></p> <div> <div><a href="https://sites.google.com/view/matseg/home#h.2otka7pobcz1"> <div> </div> </a></div> </div> <h2>Synthetic Dataset</h2> <p>The synthetic dataset is composed of synthetic scenes rendered in 2d and 3d using a blender. The synthetic data is infused with patterns, materials, and textures automatically extracted from real images allowing it to capture the complexity and diversity of the real world while maintaining the precision and scale of synthetic data. 100k images and their annotation are available to download.</p> </div> <p> </p> <p><strong>License</strong></p> <p>This dataset, including all its components, is released under the CC0 1.0 Universal (CC0 1.0) Public Domain Dedication. To the extent possible under law, the authors have dedicated all copyright and related and neighboring rights to this dataset to the public domain worldwide. This dedication applies to the dataset and all derivative works.</p> <p>The MatSeg 2D and 3D synthetic were generated using the open-images dataset which is licensed under the https://www.apache.org/licenses/LICENSE-2.0. For these components, you must comply with the terms of the Apache License. In addition, the MatSege3D dataset uses Shapenet 3D assets with GNU license.</p> <p> </p> <h3>Example Usage:</h3> <p>An Example of a training and evaluation code for a net trained on the dataset and evaluated on the benchmark is given at these urls: <a href="https://e.pcloud.link/publink/show?code=XZxIXTZG3APQej3f67JXdRjitC7zHl7jfuV">1, </a><a href="https://icedrive.net/s/RTS2xXTv1Xzh8tbxYZ9hRkGuWktj">2</a></p> <p>This include an evaluation script on the MatSeg benchmark.</p> <p>Training script using the MatSeg dataset.</p> <p>And weights of a trained model</p> <p><strong>Paper:</strong></p> <p><strong>More detail on the work ca be found in the paper<a href="https://proceedings.neurips.cc/paper_files/paper/2024/file/6ef4a4b387a5a547ea699f3df7fc1248-Paper-Datasets_and_Benchmarks_Track.pdf"> "Infusing Synthetic Data with Real-World Patterns for</a><br><a href="https://proceedings.neurips.cc/paper_files/paper/2024/file/6ef4a4b387a5a547ea699f3df7fc1248-Paper-Datasets_and_Benchmarks_Track.pdf">Zero-Shot Material State Segmentation"</a></strong></p> <p> </p> <p> </p> <p>Croissant metadata and additional sources for downloading the dataset are available at <a href="https://e.pcloud.link/publink/show?code=kZxsXTZIk88l74Jb3YeMeOcjOlJJVIqvHj7">1</a>,<a href="https://icedrive.net/s/XxgZSif7NgYRbjvDN5w9aiWZ1fR3">2</a></p> <p> </p>
Herbarium specimen segmentation dataset
<p><strong>Dataset desription</strong></p> <p>This repository contains the annotated regions of the herbarium specimen, from the Herbarium-2022 Challenge dataset [1], where only the dried and pressed plant is present.</p> <p>Each annotation has the associated image name in its filename, the images themselves can be downloaded from the kaggle page of the challenge itself, as they cannot be distributed otherwise (but are allowed for use in scientific purposes).</p> <p>The data is split into train, test and validation data in a 70%/20%/10% split and is sorted into folders accordingly.</p> <p>The annotations are contained in .txt files, and are in the YOLOv8 annotation format.</p> <p>The images were originally published in the Herbarium-2022 Challenge dataset [1].</p> <p><strong>Download and Use</strong><br>This data may be used for non-commercial research purposes only. </p> <p>[1] Brendan Hogan, damon, inversion, John Park, Riccardo de Lutio. (2022). Herbarium 2022 - FGVC9. Kaggle. https://kaggle.com/competitions/herbarium-2022-fgvc9</p> <p> </p>
PFUS1: Premier Pelvic Floor Ultrasound Segmentation Dataset
<pre><br>This dataset comprises pelvic floor ultrasound images in the midsagittal plane, involving segmentation of eight structures, from 110 patients. <br><br>The dataset is structured as follows: at the top level, there is a directory named "data" containing 110 folders, each corresponding to a patient, named "PXXX", where XXX is the patient identifier (from 000 to 109).<br><br>Each patient folder contains two files per image frame: a PNG file with the ultrasound image and a JSON file with the segmentation polygons. Each file is named "frame\_YYY\.png" or "frame\_YYY\.json" respectively, where YYY is the video frame number.<br><br>Each JSON file with the segmentation polygons is structured as a list of eight dictionaries. Each dictionary has two keys: "label" and "pol". The "label" key identifies the organ with a string, and the "pol" key is a list of pairs (x, y) defining the points list of the polygon. An example of a JSON file is shown below:<br><br><br> [<br> { <br> "pol": [[800, 400], [848, 320], ...., [796, 401]],<br> "label": "Levator ani muscle"<br> },<br> { <br> "pol": [[750, 371], [794, 384], ...., [726, 426]],<br> "label": "Rectum"<br> },<br> ...<br> ...<br> ...<br><br> ]</pre>
Land Cover Aerial Imagery (LICAID) dataset for semantic segmentation
<p><strong>Dataset Highlights:</strong></p> <ul> <li><strong>Title:</strong> Land Cover Aerial Imagery Dataset (LICAID)</li> <li><strong>Focus Area:</strong> Franciacorta wine-growing region, Lombardy, Italy</li> <li><strong>Data Source:</strong> Satellite imagery from Google Earth Pro</li> <li><strong>Classes and Descriptions:</strong> <ol> <li><strong>Grasslands:</strong> Habitats dominated by grasses, with few or no trees, found in various climates from tropical to temperate regions.</li> <li><strong>Arable Land:</strong> Land predominantly used for growing crops.</li> <li><strong>Herb-dominated Habitats:</strong> Areas where non-woody plants (herbs) are the dominant vegetation, including meadows, prairies, marshes, and wetlands.</li> <li><strong>Hedgerows:</strong> Linear strips of vegetation consisting of shrubs, small trees, and grasses, often used to mark boundaries or provide wildlife habitat in agricultural landscapes.</li> <li><strong>Vineyards:</strong> Agricultural landscapes cultivated specifically for growing grapevines, typically for wine production.</li> <li><strong>Tree-dominated Man-made Habitats:</strong> Human-modified landscapes where trees are the predominant vegetation, such as urban parks, orchards, and landscaped gardens.</li> <li><strong>Olea europaea Groves:</strong> Groves or orchards of olive trees, primarily cultivated for the production of olives and olive oil, commonly found in Mediterranean regions.</li> </ol> </li> </ul> <p><strong>gy:</strong></p> <ol> <li> <p><strong>Data Acquisition:</strong></p> <ul> <li>18 orthophoto tiles manually selected from Franciacorta.</li> <li>Satellite imagery and corresponding shape files acquired from Google Earth Pro.</li> <li>Georeferencing of imagery using ArcGIS software.</li> </ul> </li> <li> <p><strong>Data Preparation:</strong></p> <ul> <li>Segmentation using multiresolution segmentation in eCognition software.</li> <li>Validation of segmented images by a plant expert using QGIS software.</li> <li>Manual annotation of seven land cover classes.</li> </ul> </li> </ol>
polyp segmentation datasets
<p>It stores the largely used testing protocoll for polyp segmentation:</p> <p>The training set includes 900 images from Kvasir-SEG and 550 images from CVC-ClinicDB. The testing set is made of the remaining images from the above cited datasets: 100 images from Kvasir-SEG, 62 images from CVC-ClinicalDB, 380 from CVC-ColonDB, 196 from ETIS-Larib and 60 from CVC-T, which is testing set for EndoScene. </p> <p>The test sets are stored in the folder TestDataset.</p> <p>There are three versions of the training set:</p> <p>NewTRimage, original training set without data augmentation</p> <p>NewTRimageDA, data augmentation proposed in "Data augmentation for deep ensembles in polyp segmentation"</p> <p>OLDTRimage, data augmentation used in https://arxiv.org/abs/2104.00850</p> <p>The names with "mask" stores the binary mask of the related images.</p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p>
M3CropSeg: A Multi-platform, Multi-temporal, and Multi-resolution Remote Sensing Dataset for Crop Semantic to Instance and Dynamic Segmentation.
<p>Earth observation (EO) provides various multi-platform, multi-temporal, and multiresolution<br> remote sensing imagery for dynamic monitoring of planet Earth, with<br> a wide variety of uses. Crop monitoring is a typical application, which involves<br> timely gathering of the information of crop types, boundaries, and dynamic changes<br> during the whole crop growth period. However, most of the existing datasets and<br> benchmarks focus on medium-resolution (≥ 10 m) classification of the main crop<br> type by using satellite image time series (SITS), where the individual boundaries<br> (parcels) and the dynamic changes of the crop cannot be obtained, due to the<br> limited spatial resolution and the lack of multi-season annotation. In this paper,<br> a multi-platform, multi-temporal, and multi-resolution (M3) remote sensing crop<br> segmentation dataset (M3CropSeg) is introduced for very high resolution (VHR, 1<br> m) crop semantic segmentation to instance segmentation and dynamic segmentation.<br> Specifically, M3CropSeg contains 16311 pairs of airborne VHR (1 m) and SITS<br> (10 m) images, with 45 crop types and 101k instance annotations, covering a<br> 26,000 km<sup>2</sup> area of California in the U.S. M3CropSeg has various challenges,<br> including M3 data fusion, class imbalance, fine-grained classification, and multilabel<br> classification. Three tracks are designed for M3CropSeg, i.e., M3 semantic<br> segmentation, M3 instance segmentation, and M3 dynamic segmentation, to obtain<br> high-resolution pixel-level, parcel-level, and multi-season crop types, respectively.<br> The corresponding benchmarks are also provided to address the above challenges,<br> along with a variety of experimental analyses.</p>
Maize Root Domain Shift Image Datasets, Segmentation Models, and RhizoVision Explorer Settings
<p>This .zip file contains the following: 1) a .csv file used for RhizoVision Explorer settings, 2) root segmentation .pkl models developed using RootPainter, and 3) folders of maize root images collected in the field and greenhouse experiment that were used to train models and that were manually annotated to generate ground-truth datasets.</p> <p>For clarification, the segmentation model file named "000053_1679678936_V7_2021_tiled.pkl" is the growth stage-specific V7 field model. The segmentation model file named "000040_1679498247_R2_2021_tiled.pkl" is the growth stage-specific R2 field model. The segmentation model file named "000022_1679880442_V7plusR2_2021_tiled.pkl" is the fine-tuned V7+R2 field model. The segmentation model file named "000059_1687007135_V7R2_Tiled_Combined_2021.pkl" is the combined V7+R2 field model. The segmentation model file named "000068_1687361521_V7extendedR2_tiled_2021.pkl" is the extended V7+R2 field model. The segmentation model file named "000027_1681159536_GH_R2_tiled.pkl" the R2 greenhouse model. The segmentation model file named "000059_1680366870_GH_V9_tiled.pkl" is the V9 greenhouse model.</p>
Data from: Multi-contrast submillimetric 3-Tesla hippocampal subfield segmentation protocol and dataset
Open the record for dataset details and reuse information.
Ultrasound dataset for head model speed-of-sound derived from segmented MRI (MIDA model)
Open the record for dataset details and reuse information.
The A-Train Cloud Segmentation Dataset
ATCS is a dataset designed to train deep learning models to volumetrically segment clouds from multi-angle satellite imagery. The dataset consists of spatiotemporally aligned patches of multi-angle polarimetry from the POLDER sensor aboard the PARASOL mission and vertical cloud profiles from the 2B-CLDCLASS product using the cloud profiling radar (CPR) aboard CloudSat.
Small spots DeepMIB project, synthetic dataset for testing 2D semantic segmentation
<p>A complete DeepMIB project with a synthetic dataset generated for quick tests of semantic segmentation approaches.<br>The dataset includes a trained U-net network for detection of small random spots of 2 colors on a black background.</p><p>The network can be opened by loading "2D_SmallSpots_3cl_Unet.mibCfg" file by</p><ul><li><i>MIB->Menu->Tools->Deep learning segmentation->Options tab->Config files->Load </i></li><li>Drag and drop of the config file into DeepMIB window</li></ul><p>Microscopy Image Browser: <a href="https://mib.helsinki.fi">https://mib.helsinki.fi</a></p>
Large spots DeepMIB project, synthetic dataset for testing 2D patch-wise segmentation
<p>A complete DeepMIB project with a synthetic dataset generated for quick tests of the patch-wise segmentation (classification) approaches<br>The dataset includes a trained Resnet18 network for detection of patches that belong to large white spots on black background.<br>The network can be opened by loading "2D_LargeSpots_Patchwise_Resnet18.mibCfg" by</p><ul><li><i>MIB->Menu->Tools->Deep learning segmentation->Options tab->Config files->Load </i></li><li>Drag and drop of the config file into DeepMIB window</li></ul><p>Microscopy Image Browser: <a href="https://mib.helsinki.fi">https://mib.helsinki.fi</a></p>
Large Spots DeepMIB project, synthetic dataset for testing 2.5D semantic segmentation
<p>A complete DeepMIB project with a synthetic dataset generated for quick tests of 2.5D semantic segmentation approaches.<br>The dataset includes trained</p><ul><li>2.5D DeepLabV3-Resnet18 depth2color (Spots_25D_DLv3RN18_Z2C_xy200z5)</li><li>2.5D U-net depth2color (Spots_25D_Unet_Z2C_xy200z5)</li></ul><p>networkd for detection of large white 3D spots on a black background. The spots that are present on a single slice only are considered as background.</p><p>The network can be opened by loading the config files "*.mibCfg" by</p><ul><li><i>MIB->Menu->Tools->Deep learning segmentation->Options tab->Config files->Load </i></li><li>Drag and drop of the config file into DeepMIB window</li></ul><p>Microscopy Image Browser: <a href="https://mib.helsinki.fi/">https://mib.helsinki.fi</a></p>
LDD: A Grape Diseases Dataset Detection and Instance Segmentation
<p><span><span>The Instance Segmentation task, an extension of the well-known Object Detection task, is of great help in many areas, such as precision agriculture: being able to automatically identify plant organs and the possible diseases</span><br>associated with them, allows to effectively scale and automate crop monitoring and its diseases control. <br><br>To address the problem related to early disease detection and diagnosis on vines plants, a new dataset has been created with the goal of advancing the state-of-the-art of diseases recognition via instance segmentation approa<br>ches. <br><br>This was achieved by gathering images of leaves and clusters of grapes affected by diseases in their natural context. <br><br>The dataset contains photos of 10 object types which include leaves and grapes with and without symptoms of the eight more common grape diseases, with a total of 17,706 labeled instances in 1,092 images. <br><br>Multiple statistical measures are proposed in order to offer a complete view on the characteristics of the dataset. <br><br>Preliminary results for the object detection and instance segmentation tasks reached by the models Mask R-CNN and R^3-CNN are provided as baseline, demonstrating that the procedure is able to reach promising results about th<br>e objective of automatic diseases’ symptoms recognition.<br></span></p>
ForTrunkSpecies - Image datasets of annotated RGB(-NIR) images for tree trunk types detection and segmentation at ground-level
<p>Two annotated image datasets for detection and segmentation of two tree trunk species - eucalyptus and pine:</p> <ul> <li>ForSpeciesDet(_4channels): dataset for tree trunk species detection in RGB(-NIR) images;</li> <li>ForSpeciesSeg(_4channels): dataset for tree trunk species segmentation in RGB(-NIR) images.</li> </ul>
Training dataset for Carotid Vessel Wall Segmentation and Atherosclerosis Diagnosis Challenge, MICCAI 2022
<p>Training dataset for <strong>Carotid Vessel Wall Segmentation and Atherosclerosis Diagnosis Challenge, MICCAI 2022</strong>. </p> <p>Please refer to our website: <strong>https://vessel-wall-segmentation-2022.grand-challenge.org/</strong>.</p>
Event Registry dataset texts with OCR degradations and synthesised segmentation
<p>This is the text of the Event Registrt dataset dedicated to fake news detection that has been updated to be used in event detection.</p> <p>Rupnik, Jan, Andrej Muhic, Gregor Leban, Primoz Skraba, Blaz Fortuna, et Marko Grobelnik. 2016. « News Across Languages - Cross-Lingual Document Similarity and Event Tracking ». <em>Journal of Artificial Intelligence Research</em> 55 (janvier): 283‑316. <a href="https://doi.org/10.1613/jair.4780">https://doi.org/10.1613/jair.4780</a>.</p> <p>Miranda, Sebastião, Artūrs Znotiņš, Shay B. Cohen, et Guntis Barzdins. 2018. « Multilingual Clustering of Streaming News ». In <em>2018 Conference on Empirical Methods in Natural Language Processing</em>, 4535‑44. Brussels, Belgium: Association for Computational Linguistics. <a href="https://www.aclweb.org/anthology/D18-1483/">https://www.aclweb.org/anthology/D18-1483/</a>.</p> <p>Guillaume Bernard. (2022). Event Registry titles only dataset with multiple extracted features (both sparse and dense) (1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.6630447</p> <p>Some degradations are applied using the DocCreator [1] tool in order to degrade the text of the tweets and to reproduce some common errors found in OCRised documents [2].</p> <p>[1]: Journet, Nicholas, Muriel Visani, Boris Mansencal, Kieu Van-Cuong, et Antoine Billy. 2017. « DocCreator: A New Software for Creating Synthetic Ground-Truthed Document Images ». <em>Journal of Imaging</em> 3 (4): 62. <a href="https://doi.org/10.3390/jimaging3040062">https://doi.org/10.3390/jimaging3040062</a>.</p> <p>[2]: Linhares Pontes, Elvys, Ahmed Hamdi, Nicolas Sidere, et Antoine Doucet. 2019. « Impact of OCR Quality on Named Entity Linking ». In <em>Digital Libraries at the Crossroads of Digital Information for the Future</em>, 11853:102‑15. Lecture Notes in Computer Science. Cham: Springer International Publishing. <a href="https://doi.org/10.1007/978-3-030-34058-2_11">https://doi.org/10.1007/978-3-030-34058-2_11</a>.</p> <p>The results of the OCR degradations are as follow:</p> <table> <caption>Event Registry CER/WER</caption> <tbody> <tr> <td> </td> <td> </td> <td>Without</td> <td>Character degradation</td> <td>Phantom degradation</td> <td>Bleed</td> <td>Blur</td> <td>All</td> </tr> <tr> <td>Event Registry</td> <td>CER</td> <td>0.282</td> <td>4.154</td> <td>0.274</td> <td>0.275</td> <td>0.582</td> <td>4.577</td> </tr> <tr> <td>Event Registry</td> <td>WER</td> <td>0.552</td> <td>16.364</td> <td>0.551</td> <td>0.548</td> <td>1.159</td> <td>16.974</td> </tr> </tbody> </table> <p> </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.