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.
16
datasets available to search
ShareScore release 0.9.0
Dataset results
16 results for “few-shot learning”
MEWL: Few-shot multimodal word learning with referential uncertainty
<p><strong>Dataset Release for <a href="https://arxiv.org/abs/2306.00503">MEWL: Few-shot multimodal word learning with referential uncertainty (ICML 2023) </a></strong></p> <p><strong>GitHub:</strong> <a href="https://github.com/jianggy/MEWL">https://github.com/jianggy/MEWL</a></p> <p><strong>Abstract: </strong>Without explicit feedback, humans can rapidly learn the meaning of words. Children can acquire a new word after just a few passive exposures, a process known as fast mapping. This word learning capability is believed to be the most fundamental building block of multimodal understanding and reasoning. Despite recent advancements in multimodal learning, a systematic and rigorous evaluation is still missing for human-like word learning in machines. To fill in this gap, we introduce the MachinE Word Learning (MEWL) benchmark to assess how machines learn word meaning in grounded visual scenes. MEWL covers human's core cognitive toolkits in word learning: cross-situational reasoning, bootstrapping, and pragmatic learning. Specifically, MEWL is a few-shot benchmark suite consisting of nine tasks for probing various word learning capabilities. These tasks are carefully designed to be aligned with the children's core abilities in word learning and echo the theories in the developmental literature. By evaluating multimodal and unimodal agents' performance with a comparative analysis of human performance, we notice a sharp divergence in human and machine word learning. We further discuss these differences between humans and machines and call for human-like few-shot word learning in machines.</p>
learn2learn: Few-Shot Learning Datasets
<p>Few-shot learning datasets, including:</p> <ul> <li>mini-ImageNet</li> <li>tiered-ImageNet</li> <li>CIFAR-FS</li> <li>FC100</li> </ul> <p>New in 1.0.1:</p> <ul> <li>FGVC Fungi</li> <li>FGVC Aircrafts</li> <li>Describable Textures</li> <li>VGG Flowers</li> <li>CUB200</li> </ul> <p>Please cite the respective datasets if you use them, not this archive.</p>
An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environments
<p>The problem of training a deep neural network with a small set of positive samples is known as few-shot learning (FSL). It is widely known that traditional deep learning (DL) algorithms usually show very good performance when trained with large datasets. However, in many applications, it is not possible to obtain such a high number of samples. In the image domain, typical FSL applications are those related to face recognition. In the audio domain, music fraud or speaker recognition can be clearly benefited from FSL methods. This paper deals with the application of FSL to the detection of specific and intentional acoustic events given by different types of sound alarms, such as door bells or fire alarms, using a limited number of samples. These sounds typically occur in domestic environments where many events corresponding to a wide variety of sound classes take place. Therefore, the detection of such alarms in a practical scenario can be considered an open-set recognition (OSR) problem. To address the lack of a dedicated public dataset for audio FSL, researchers usually make modifications on other available datasets. This paper is aimed at providing the audio recognition community with a carefully annotated dataset for FSL and OSR comprised of 1360 clips from 34 classes divided into pattern sounds and unwanted sounds. To facilitate and promote research in this area, results with two baseline systems (one trained from scratch and another based on transfer learning), are presented.</p> <p> </p>
Supporting information for "Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa"
<p><strong>Description</strong></p> <p>In this work, we use few-shot learning to segment the body and vein architecture of <em>P. trichocarpa</em> leaves from high-resolution scans obtained in the UC Davis common garden. Leaf and vein segmentation are formulated as separate tasks, in which convolutional neural networks (CNNs) are used to iteratively expand partial segmentations until reaching stopping criteria. Our leaf and vein segmentation approaches use just 50 and 8 manually traced images for training, respectively, and are applied to a set of 2,634 top and bottom leaf scans. We show that both methods achieve high segmentation accuracy and retain biologically realistic features. The leaf and vein segmentations are compared against a U-Net baseline model, and subsequently used to extract 68 morphological traits using traditional open-source image processing tools, which are validated using real-world physical measurements. For a biological perspective, we perform a genome-wide association study using the "vein density" trait to discover novel genetic architectures associated with multiple physiological processes relating to leaf development and function. In addition to sharing all of the few-shot learning code, we are releasing all images, manual segmentations, model predictions, 68 extracted leaf phenotypes, and a new set of SNPs called against the v4 <em>P. trichocarpa</em> genome for 1,419 genotypes.</p> <p><strong>Directories:</strong></p> <pre><code>Few-shot learning for p. trichocarpa leaf traits ├── data │ ├── genomes │ │ ├── Ptri_V4_Nisq1.[...].bed │ │ ├── Ptri_V4_Nisq1.[...].bim │ │ └── Ptri_V4_Nisq1.[...].fam │ ├── images │ │ └── *.jpeg │ ├── leaf_masks │ │ └── *.png │ ├── leaf_preds │ │ └── *.png │ ├── leaf_unet_preds │ │ └── *.png │ ├── results │ │ ├── digital_traits.tsv │ │ ├── gwas_results.csv │ │ ├── manual_traits.tsv │ │ ├── vein_density_blups.tsv │ │ └── vein_density_tps_adj.tsv │ ├── vein_bce_preds │ │ └── *.png │ ├── vein_bce_probs │ │ └── *.png │ ├── vein_fl_preds │ │ └── *.png │ ├── vein_fl_probs │ │ └── *.png │ ├── vein_masks │ │ └── *.png │ ├── vein_unet_bce_preds │ │ └── *.png │ ├── vein_unet_bce_probs │ │ └── *.png │ ├── vein_unet_fl_preds │ │ └── *.png │ ├── vein_unet_fl_probs │ │ └── *.png ├── figures │ └── *.png ├── logs │ ├── leaf_tracer_256.txt │ ├── leaf_unet_256.txt │ ├── vein_grower_bce_128.txt │ ├── vein_grower_fl_128.txt │ ├── vein_unet_bce_128.txt │ └── vein_unet_fl_128.txt ├── models │ ├── BuildCNN.py │ ├── BuildUNet.py │ ├── LeafTracer.py │ └── VeinGrower.py ├── notebooks │ ├── Figures.ipynb │ ├── GrowerInference.ipynb │ ├── GrowerTraining.ipynb │ ├── TracerInference.ipynb │ ├── TracerTraining.ipynb │ ├── UNetLeafSegmentation.ipynb │ └── UNetVeinSegmentation.ipynb ├── utils │ ├── GetLowestGPU.py │ ├── ImageLoader.py │ ├── LeafGenerator.py │ ├── ModelWrapperGenerator.py │ ├── TimeRemaining.py │ ├── TraceInitializer.py │ ├── UNetTileGenerator.py │ └── VeinGenerator.py └── weights ├── leaf_tracer_256_best_val_model.save ├── leaf_unet_256_best_val_model.save ├── vein_grower_bce_128_best_val_model.save ├── vein_grower_fl_128_best_val_model.save ├── vein_unet_bce_128_best_val_model.save └── vein_unet_fl_128_best_val_model.save </code></pre> <p><strong>Data:</strong></p> <p>The <code>data</code> folder includes all images, ground truth segmentations, predicted segmentations, and extracted leaf traits. All images encode the sample ID in the file name by indicating the treatment, block, row, position, and leaf side, respectively. For example, the file, <code>C_1_1_2_bot.jpeg</code>, indicates the control treatment, block 1, row 1, position 2, and the bottom side of the leaf. Tabulated results include position IDs as well as the corresponding genotype IDs.</p> <ul> <li>The <code>images</code> folder includes the 2,906 high-resolution leaf scans taken in the field.</li> <li>The <code>leaf_masks</code> folder includes 50 ground truth segmentations used for training the leaf tracing algorithm.</li> <li>The <code>leaf_preds</code> folder includes the 2,906 predicted segmentations from the leaf tracing algorithm.</li> <li>The <code>leaf_unet_preds</code> folder includes the 2,906 predicted segmentations from the U-Net model for leaf segmentation.</li> <li>The <code>vein_masks</code> folder includes 8 ground truth segmentations used for training the vein growing algorithm.</li> <li>The <code>vein_*_preds</code> folder includes the 1,453 predicted segmentations from the vein growing algorithm, where * specifies the loss function (bce: binary cross-entropy, fl: focal loss).</li> <li>The <code>vein_*_probs</code> folder includes the 1,453 predicted probability maps from the vein growing algorithm before thresholding, where * specifies the loss function (bce: binary cross-entropy, fl: focal loss).</li> <li>The <code>vein_unet_*_preds</code> folder includes the 1,453 predicted segmentations from the U-Net model for vein segmentation, where * specifies the loss function (bce: binary cross-entropy, fl: focal loss).</li> <li>The <code>vein_unet_*_probs</code> folder includes the 1,453 predicted probability maps from the U-Net model for vein segmentation before thresholding, where * specifies the loss function (bce: binary cross-entropy, fl: focal loss).</li> <li>The <code>genomes</code> folder includes the set of SNPs called against the v4 <em>P. trichocarpa</em> genome for 1,419 genotypes with a README file detailing the steps taken.</li> <li>The <code>results</code> folder includes <ul> <li>Raw values of the 68 predicted leaf traits in <code>digital_traits.tsv</code></li> <li>Manually measured values of petiole length and width in <code>manual_traits.tsv</code></li> <li>Thin plate spline (TPS) adjusted values of the vein density trait in <code>vein_density_tps_adj.tsv</code></li> <li>Best linear unbiased prediction (BLUP) adjusted values of the vein density trait in <code>vein_density_blups.tsv</code></li> <li>GWAS results for the vein density trait, including chromosome positions and corresponding P values, in <code>gwas_results.csv</code></li> </ul> </li> </ul> <p><strong>Figures:</strong></p> <p>The <code>figures</code> folder includes all figures and videos used in the manuscript. See <code>notebooks/Figures.ipynb</code> for the methods used to generate these figures.</p> <p><strong>Logs:</strong></p> <p>The <code>logs</code> folder includes logs of CNN convergence for the training and validation sets during model training for the leaf tracing CNN vein growing CNN, and U-Net models. The file names include the model, loss function (bce: binary cross-entropy, fl: focal loss), and size of the input window for each method (e.g., 128 for the vein growing CNN).</p> <p><strong>Models:</strong></p> <p>The <code>models</code> folder includes the CNN implementations in PyTorch as well as the leaf tracing and vein growing algorithms at inference time.</p> <ul> <li><code>BuildCNN.py</code> defines the CNN architecture for leaf tracing or vein growing, with user-specified input shape, output shape, layers, and output activation functions.</li> <li><code>BuildUNet.py</code> defines the U-Net architecture for leaf and vein segmentation, with user-specified input/output shape, layers, and output activation functions.</li> <li><code>LeafTracer.py</code> defines the leaf tracing algorithm at inference time.</li> <li><code>VeinGrower.py</code> defines the vein growing algorithm at inference time.</li> </ul> <p><strong>Notebooks:</strong></p> <p>The <code>notebooks</code> folder includes Jupyter notebooks used for model training, model inference, and figure generation.</p> <ul> <li><code>Figures.ipynb</code> is used to generate all of the manuscript figures.</li> <li><code>GrowerTraining.ipynb</code> is used to train the vein growing CNN.</li> <li><code>GrowerInference.ipynb</code> is used to apply the vein growing algorithm to the 1,453 leaf bottom images.</li> <li><code>TracerTraining.ipynb</code> is used to train the leaf tracing CNN.</li> <li><code>TracerInference.ipynb</code> is used to apply the leaf tracing algorithm to the 2,906 leaf top and bottom images.</li> <li><code>UNetLeafSegmentation.ipynb</code> is used to train and apply U-Net for leaf segmentation.</li> <li><code>UNetVeinSegmentation.ipynb</code> is used to train and apply U-Net for vein segmentation.</li> </ul> <p><strong>Utils:</strong></p> <p>The <code>utils</code> folder includes utility scripts implemented in Python that assist in model training and inference.</p> <ul> <li><code>ImageLoader.py</code> loads image/mask pairs for sampling training/validation tiles.</li> <li><code>LeafGenerator.py</code> generates inputs/outputs for the leaf tracing CNN.</li> <li><code>VeinGenerator.py</code> generates inputs/outputs for the vein growing CNN.</li> <li><code>UNetTileGenerator.py</code> generates inputs/outputs for the U-Net model.</li> <li><code>GetLowestGPU.py</code> identifies available GPUs using the <code>nvidia-smi</code> command and selects the one with lowest memory usage, if none available the device is set to CPU.</li> <li><code>ModelWrapperGenerator.py</code> wraps the PyTorch CNN and data loaders with similar functionality to the Keras Model class in TensorFlow (e.g., model.fit(...)).</li> <li><code>TimeRemaining.py</code> is used by the model wrapper to estimate remaining time left per epoch.</li> <li><code>TraceInitializer.py</code> is used by the tracing algorithm at inference time to initialize the leaf trace using automatic thresholding.</li> </ul> <p><strong>Weights:</strong></p> <p>The <code>weights</code> folder includes the CNN parameters from the epoch resulting in the best validation error. The file names include the model, loss function (bce: binary cross-entropy, fl: focal loss), and size of the input window for each method (e.g., 128 for the vein growing CNN). The weights are loaded into the CNN models for inference.</p> <p><strong>Citation:</strong></p> <pre><code>@article{ doi:10.34133/plantphenomics.0072, author = {John Lagergren and Mirko Pavicic and Hari B. Chhetri and Larry M. York and Doug Hyatt and David Kainer and Erica M. Rutter and Kevin Flores and Jack Bailey-Bale and Marie Klein and Gail Taylor and Daniel Jacobson and Jared Streich }, title = {Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa}, journal = {Plant Phenomics}, volume = {0}, number = {ja}, pages = {}, year = {}, doi = {10.34133/plantphenomics.0072}, URL = {https://spj.science.org/doi/abs/10.34133/plantphenomics.0072}, eprint = {https://spj.science.org/doi/pdf/10.34133/plantphenomics.0072}, }</code></pre>
Few-Shot Learning for Issue Report Classification
<p>This dataset is a sample of the NLBSE23 dataset for Issue Report Classification, manually re-labeled.</p>
Delaunay data set learn2learn l2l for meta-learning and few-shot learning
<p>Delaunay data set learn2learn l2l for meta-learning and few-shot learning. We split it into 3 meta-train, meta-val and meta-test sets. </p> <p> </p> <p>For details of original data see: https://github.com/camillegontier/DELAUNAY_dataset</p>
Supporting information for "Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa"
<p>Raw VCF file for <em>Populus trichocarpa</em> V4 SNPs - Biallelic SNP variants were called for 1492 Populus trichocarpa genotypes using GATK Version 4.0 software.</p>
Explainable few-shot learning workflow for detecting invasive and exotic tree species
<p>This is the supporting dataset of research work: <a href="Link"><strong>Explainable few-shot learning workflow for detecting</strong></a> <a href="Link"><strong>invasive and exotic tree species</strong></a>. (Link to be added after the publication) In this research, we presents a workflow that tackles both challenges by proposing an explainable few-shot learning workflow for detecting invasive and exotic tree species in the Atlantic Forest of Brazil using Unmanned Aerial Vehicle (UAV) images. By integrating a Siamese network with explainable AI (XAI), the workflow enables the classification of tree species with minimal labeled data while providing visual, case-based explanations for the predictions.</p> <p>The workflow is accessible in <a href="Link">this GitHub repository</a> (Link to be added after the publication). The required dataset of this workflow in provided in this Zenodo repository.</p> <p>This dataset repository has the following contents</p> <ul> <li> <p>uav_img.zip: the UAV orthomosaic image (.tif) of the study area used in this research, with related metadata</p> </li> <li>tree_labels.zip: the labels of trees created by expert, available in .shp and .gpkg</li> <li> <p>cutouts.zip: tree cutouts used in this study. They are two sub-directories:</p> <ul> <li>all_cutouts: all the candidated cutouts from three sources. See the README.md file insisde this folder for more information</li> <li>selected cutout: the manually selected cutouts from all cutouts used for training.</li> </ul> </li> <li> <p>training_pairs_20000.zarr.zip: training data created for base network traning. It is created by pairing the selected cutouts.</p> </li> <li>netflora.zip: Netflora workflow prediction results</li> <li>optimized_models.zip: Optimized base models (shallow and deep) and refined models with different shots/fold setup.</li> <li>n_fold_x_validation.zip: data pairs for refinement traing, with n fold and x valiation setup.</li> </ul>
PRICER: Leveraging Few-Shot Learning with Fine-Tuned Large Language Models for Unstructured Economic Data
<p>Describes the taxonomy used in the paper "PRICER: Leveraging Few-Shot Learning with Fine-Tuned Large Language Models for Unstructured Economic Data", presented at the Second Workshop on Semantic Technologies and Deep Learning Models for Scientific, Technical and Legal Data<em> </em>at the Extended Semantic Web Conference (ESWC) 2024.</p>
OpenEarthMap Land Cover Mapping Few-Shot Learning Challenge
<pre><strong>***The challenge is over, please use this verion for post-challenge research. This version contains all the data and files, <br>except the labels of the query-set of the testset that are withheld and researchers can submit the predictions at the <br>challenge leaderboard for evaluation***</strong></pre> <p><strong>Overview</strong></p> <p>This challenge is co-organized with the <a href="https://sites.google.com/view/l3divu2024/overview" target="_blank" rel="noopener">L3D-IVU 2024 CVPR</a> workshop. The challenge is an extension of the <a href="https://open-earth-map.org/" target="_blank" rel="noopener">OpenEarthMap </a>benchmark dataset for a generalized few-shot semantic segmentation (GFSS) task. The challenge aims to evaluate and benchmark learning methods for few-shot semantic segmentation on the OpenEarthMap dataset to promote research on geoinformatics for social good. The motivation is to enable researchers to develop few-shot learning algorithms for high-resolution RS image semantic segmentation.</p> <p><strong>Page</strong></p> <p><a href="https://cliffbb.github.io/OEM-Fewshot-Challenge/" target="_blank" rel="noopener">https://cliffbb.github.io/OEM-Fewshot-Challenge/</a></p> <p><strong>Baseline</strong></p> <p>The baseline model for the challenge is available <a href="https://github.com/cliffbb/OEM-Fewshot-Challenge" target="_blank" rel="noopener">here</a>.</p> <p><strong>Leaderboard</strong></p> <p>The <a href="https://codalab.lisn.upsaclay.fr/competitions/19210" target="_blank" rel="noopener">challenge leaderboard </a>is opened for post-challenge research to enable researchers to evaluate the predictions on the query-set of the testset.</p> <p><strong>Description</strong></p> <p>The dataset has been designed for remote sensing few-shot learning, particularly, for GFSS tasks in land cover mapping. The dataset consists of only 408 samples from the original <a href="https://open-earth-map.org/" target="_blank" rel="noopener">OpenEarthMap</a> dataset for RS image semantic segmentation. It extends the original 8 semantic classes of the OpenEarthmap benchmark to 15 classes, which is split into 7:4:4 for <em>train_base_class</em>, <em>val_novel_class</em>, and <em>test_novel_class</em> disjointed sets, respectively (i.e., <em>train_base_class</em> ∩ <em>val_novel_class</em> ∩ <em>test_novel_class</em> = ∅). The 408 samples are also split into 258 as `trainset`, 50 as `valset`, and 100 as `testset`. The `trainset` is for pre-training a backbone network. It contains only the images and labels of the <em>train_base_class</em> split. Both the `valset` and the `testset` consist of a <em>support set</em> and a <em>query set</em> for a <strong>5-shot</strong> with <strong>4 novel classes</strong> and <strong>7 base classes</strong> GFSS task. The `valset` and the `testset` contain the images and labels of the <em>val_novel_class</em> and the <em>test_novel_class</em> splits, respectively.</p> <p>The challenge is in two phases: development phase and evaluation phase. The `valset` is for the development phase and the `testsets` is for the evaluation phase. Both `valset` and `testset` have 20 image-label pair examples, 5-set examples for each of the 4 novel classes in the <em>support set</em>. The `valset` and the `testset` contain an additional 30 images and 80 images, respectively, in the <em>query set</em>, which are to be predicted using the 20 labelled images in their <em>support set</em>. The labels for each image in the <em>support sets</em> do not contain any of the <em>train_base_class</em> split. Also, in each 5-set examples, the labels contain only one novel class (i.e., one novel class per 5-set examples). However, in the `valset`, the labels for the images in the <em>query set</em> contain both <em>train_base_class</em> and <em>val_novel_class</em>; and in the `testset, the labels for the images in the <em>query set</em> contain both <em>train_base_class</em> and <em>test_novel_class</em> `. Note that both the <em>support set</em> and <em>query set</em> in the `valset` are different from the ones in the `testset`.</p> <pre><br>File Structure and Content (All files are in `.tif` format): ----------------------------------------------------------- 1. **trainset.zip**: - Contains `images` and `labels` folders - `images` folder: 258 images of size 1024x1024 with a GSD (Ground Sampling Distance) of 0.6-1m.<br> - `labels` folder: 258 segmentation masks of the images in the `images` folder. 2. **valset.zip**:<br> - Contains `images` and `labels` folders<br> - `images` folder: 50 images of size 1024x1024 with a GSD (Ground Sampling Distance) of 0.6-1m.<br> - `labels` folder: 20 labels of the ``support set`` images in the `images` folder. The labels for<br> the 30 ``query set`` images in the `images` folder are withheld.<br>3. **testset.zip**:<br> - Contains `images` and `labels` folders<br> - `images` folder: 100 images of size 1024x1024 with a GSD (Ground Sampling Distance) of 0.6-1m.<br> - `labels` folder: 20 labels of the ``support set`` images in the `images` folder. The labels for<br> the 80 ``query set`` images in the `images` folder are withheld.<br> 4. **train.txt**:<br> - Contains a list of file names in the `trainset.zip`.<br> <br>3. **val.json** and **test.json**:<br> - Contains a list of file names the in the `valset.zip` and `testset.zip`, respectively. Below is<br> the structure of the `val.json` and `test.json` files.<br> - fnames = {<br> {"support_set": {8: ["filename_1.tif", "filename_2.tif", ...., "filename_5.tif"],<br> 9: ["filename_1.tif", "filename_2.tif", ...., "filename_5.tif"],<br> 10: ["filename_1.tif", "filename_2.tif", ...., "filename_5.tif"],<br> 11: ["filename_1.tif", "filename_2.tif", ...., "filename_5.tif"]},<br> {"query_set": ["filename_1.tif", "filename_2.tif", "filename_3.tif", ...<br> ...., <br> "filename_n.tif"]} <br> }<br> Land Cover Mapping Classes Strucure: ------------------------------------<br>1. **The `trainset`:<br> classId2className = {<br> # ***Base classes*** 1: 'tree', 2: 'rangeland', 3: 'bareland', 4: 'agric land type 1', 5: 'road type 1', 6: 'sea, lake, & pond', 7: 'building type 1'<br> }<br><br>2. **The `valset` and `testset`:<br> classId2className = {<br> # ***Base classes*** 1: 'tree', 2: 'rangeland', 3: 'bareland', 4: 'agric land type 1', 5: 'road type 1', 6: 'sea, lake, & pond', 7: 'building type 1'<br> # ***Novel classes***<br> 8: '',<br> 9: '',<br> 10: '',<br> 11: ''<br> }<br><br> - The class names for the ***Novel classes*** depends on the data set.<br><br> For the `valset`, the class names can be updated as:<br> {<br> 8: 'road type 2',<br> 9: 'river',<br> 10: 'boat & ship',<br> 11: 'agric land type 2'<br> }<br><br> For the `testset`, the class names can be updated as:<br> {<br> 8: 'vehicle & cargo-trailer',<br> 9: 'parking space',<br> 10: 'sports field',<br> 11: 'building type 2'<br> }<br><br><strong>License</strong></pre> <p>See <a href="../records/7223446" target="_blank" rel="noopener">OpenEarthMap</a></p>
Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility
<p>This upload contains 1) the used thematic maps in the study, 2) the samples to train and validate the proposed model, and 3) the samples used to predict landslide susceptibility of Fengjie County and Fuling District. The code related to the methods is available on the website: <a href="https://github.com/Young-Excavator/Meta_LSM">https://github.com/Young-Excavator/Meta_LSM</a>.</p>
Few-Shot Meta-Learning Applied to Whole Brain Activity Maps Improves Systems Neuropharmacology and Drug Discovery
<p>Data and Code are all included</p>
Discovery of antimicrobial peptides targeting Acinetobacter baumannii via a pre-trained and fine-tuned few-shot learning-based pipeline
GEO Series GSE306268. Acinetobacter baumannii. 6 samples. Type: Expression profiling by high throughput sequencing.
Replication Package - Illicit Content Recognition with Few-shot Learning
<p>Replication package and dataset for the paper: When the Few Outweigh the Many: Illicit Content Recognition with Few-shot Learning</p>
PAN23 Profiling Cryptocurrency Influencers with Few-shot Learning
<p>This is the dataset for the shared task on <a href="https://pan.webis.de/clef23/pan23-web/author-profiling.html#">Profiling Cryptocurrency Influencers with Few-shot Learning</a>. Please consult the task's page for further details on the format, the dataset's creation, and links to baselines and utility code.</p> <p> </p> <p><strong>Task</strong>: In this shared task we aim to profile cryptocurrency influencers in social media, from a low-resource perspective. Moreover, we propose to categorize other related aspects of the influencers, also using a low-resource setting. Specifically, we focus on English Twitter posts for three different sub-tasks:</p> <ol> <li><strong>Low-resource influencer profiling (subtask1):</strong> <ul> <li>Input:<br> 32 users per label with a maximum of 10 English tweets each.<br> Classes: (1) null, (2) nano, (3) micro, (4) macro, (5) mega</li> <li>Official evaluation metric: Macro F1</li> <li>Submission: TIRA.</li> <li>Baselines: User-character Logistic Regression; <a href="https://huggingface.co/sentence-transformers/sentence-t5-large">t5-large</a> (bi-encoders) - zero shot [7], <a href="https://huggingface.co/sentence-transformers/sentence-t5-large">t5-large</a> (label tuning) - few shot [7]</li> </ul> </li> <li><strong>Low-resource influencer interest identification (subtask2):</strong> <ul> <li>Input:<br> 64 users per label with 1 English tweet each.<br> Classes: (1) technical information, (2) price update, (3) trading matters, (4) gaming, (5) other</li> <li>Official evaluation metric: Macro F1</li> <li>Submission: TIRA.</li> <li>Baselines: User-character Logistic Regression; <a href="https://huggingface.co/sentence-transformers/sentence-t5-large">t5-large</a> (bi-encoders) - zero shot [7], <a href="https://huggingface.co/sentence-transformers/sentence-t5-large">t5-large</a> (label tuning) - few shot [7]</li> </ul> </li> <li><strong>Low-resource influencer intent identification (subtask3):</strong> <ul> <li>Input:<br> 64 users per label with 1 English tweets each.<br> Classes: (1) subjective opinion, (2) financial information, (3) advertising, (4) announcement</li> <li>Official evaluation metric: Macro F1</li> <li>Submission: TIRA.</li> <li>Baselines: User-character Logistic Regression; <a href="https://huggingface.co/sentence-transformers/sentence-t5-large">t5-large</a> (bi-encoders) - zero shot [7], <a href="https://huggingface.co/sentence-transformers/sentence-t5-large">t5-large</a> (label tuning) - few shot [7]</li> </ul> </li> </ol> <p><strong>Versioning:</strong> </p> <ul> <li>1.0: initial upload</li> <li>1.1 fixed a minor bug where some users contained some non-English text. Since English is the target language in the competition, all non-English texts have been replaced or removed. </li> </ul>
Predicting the tensile properties of Wood Plastic Composites using material extrusion with Meta-based Few-Shot Learning
Open the record for dataset details and reuse information.
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.