데이터셋 탐색

MORPH is a facial age estimation dataset, which contains 55,134 facial images of 13,617 subjects ranging from 16 to 77 years old. Source: Deep Ordinal Regression Forests Image Source: https://uncw.edu/oic/tech/morph.html

The Neuromorphic-Caltech101 (N-Caltech101) dataset is a spiking version of the original frame-based Caltech101 dataset. The original dataset contained both a "Faces" and "Faces Easy" class, with each consisting of different versions of the same images. The "Faces" class has been removed from N-Caltech101 to avoid confusion, leaving 100 object classes plus a background class. The N-Caltech101 dataset was captured by mounting the ATIS sensor on a motorized pan-tilt unit and having the sensor move while it views Caltech101 examples on an LCD monitor as shown in the video below. A full description of the dataset and how it was created can be found in the paper below. Please cite this paper if you make use of the dataset.

The Synthetic Morphing Attack Detection Development (SMDD) dataset is a synthetic-based MAD dataset, consisting of 25k bona-fide images generated using the StyleGAN2-ADA framework and 15k morphing attacks created from the bonafide samples using the OpenCV morphing technique.

Brief Description The Neuromorphic-MNIST (N-MNIST) dataset is a spiking version of the original frame-based MNIST dataset. It consists of the same 60 000 training and 10 000 testing samples as the original MNIST dataset, and is captured at the same visual scale as the original MNIST dataset (28x28 pixels). The N-MNIST dataset was captured by mounting the ATIS sensor on a motorized pan-tilt unit and having the sensor move while it views MNIST examples on an LCD monitor as shown in this video. A full description of the dataset and how it was created can be found in the paper below. Please cite this paper if you make use of the dataset. Orchard, G.; Cohen, G.; Jayawant, A.; and Thakor, N. “Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades", Frontiers in Neuroscience, vol.9, no.437, Oct. 2015

FERET-Morphs is a dataset of morphed faces selected from the publicly available FERET dataset [1]. We created the database by selecting similar looking pairs of people, and made 3 types of morphs for each pair using the following morphing tools: OpenCV [2], FaceMorpher [3], StyleGAN 2 [3]. * [1] https://www.nist.gov/itl/products-and-services/color-feret-database * [2] https://www.learnopencv.com/face-morph-using-opencv-cpp-python * [3] https://github.com/yaopang/FaceMorpher/tree/master/facemorpher * [4] https://github.com/NVlabs/stylegan2

The Universal Morphology (UniMorph) project is a collaborative effort to improve how NLP handles complex morphology in the world’s languages. The goal of UniMorph is to annotate morphological data in a universal schema that allows an inflected word from any language to be defined by its lexical meaning, typically carried by the lemma, and by a rendering of its inflectional form in terms of a bundle of morphological features from our schema. The specification of the schema is described here and in Sylak-Glassman (2016).

FRLL-Morphs is a dataset of morphed faces based on images selected from the publicly available Face Research London Lab dataset [1]. We created the database by selecting similar looking pairs of people, and made 4 types of morphs for each pair using the following morphing tools: OpenCV [2], FaceMorpher [3], StyleGAN 2 [3], WebMorpher [4]. * [1] https://figshare.com/articles/dataset/Face_Research_Lab_London_Set/5047666 * [2] https://www.learnopencv.com/face-morph-using-opencv-cpp-python * [3] https://github.com/yaopang/FaceMorpher/tree/master/facemorpher * [4] https://github.com/NVlabs/stylegan2

Named Entity (NER) annotations of the Hebrew Treebank (Haaretz newspaper) corpus, including: morpheme and token level NER labels, nested mentions, and more. We publish the NEMO corpus in the TACL paper "Neural Modeling for Named Entities and Morphology (NEMO^2)" [1], where we use it in extensive experiments and analyses, showing the importance of morphological boundaries for neural modeling of NER in morphologically rich languages. Code for these models and experiments can be found in the NEMO code repo. ## Main features: 1. Morpheme, token-single and token-multi sequence labels. Morpheme labels provide exact boundaries, token-multi provide partial sub-word morphological but no exact boundaries, token-single provides only token-level information. 1. All annotations are in BIOSE format (B=Begin, I=Inside, O=Outside, S=Singleton, E=End). 1. Widely-used OntoNotes entity category set: GPE (geo-political entity), PER (person), LOC (location), ORG (organization), FAC (facility), EVE (event), WOA (work-of-art), ANG (language), DUC (product). 1. NEMO includes NER annotations for the two major versions of the Hebrew Treebank, UD (Universal Dependency) and SPMRL. These can be aligned to the other morphosyntactic information layers of the treebank using bclm 1. We provide nested mentions. Only the first, widest, layer is used in the NEMO^2 paper. We invite you to take on this challenge! 1. Guidelines used for annotation are provided here. 1. Corpus was annotated by two native Hebrew speakers of academic education, and curated by the project manager. We provide the original annotations made by the annotators as well to promote work on learning with disagreements. 1. Annotation was performed using WebAnno (version 3.4.5) ## Basic Corpus Statistics | | train | dev | test | |------------------------------| --:| --:| --:| | Sentences | 4,937 | 500 | 706 | | Tokens | 93,504 | 8,531 | 12,619 | | Morphemes | 127,031 | 11,301 | 16,828 | | All mentions | 6,282 | 499 | 932 | | Type: Person (PER) | 2,128 | 193 | 267 | | Type: Organization (ORG) | 2,043 | 119 | 408 | | Type: Geo-Political (GPE) | 1,377 | 121 | 195 | | Type: Location (LOC) | 331 | 28 | 41 | | Type: Facility (FAC) | 163 | 12 | 11 | | Type: Work-of-Art (WOA) | 114 | 9 | 6 | | Type: Event (EVE) | 57 | 12 | 0 | | Type: Product (DUC) | 36 | 2 | 3 | | Type: Language (ANG) | 33 | 3 | 1 | ## Evaluation An evaluation script is provided in the NEMO code repo along with evaluation instructions. ## Citation @article{10.1162/tacl_a_00404, author = {Bareket, Dan and Tsarfaty, Reut}, title = "{Neural Modeling for Named Entities and Morphology (NEMO2)}", journal = {Transactions of the Association for Computational Linguistics}, volume = {9}, pages = {909-928}, year = {2021}, month = {09}, abstract = "{Named Entity Recognition (NER) is a fundamental NLP task, commonly formulated as classification over a sequence of tokens. Morphologically rich languages (MRLs) pose a challenge to this basic formulation, as the boundaries of named entities do not necessarily coincide with token boundaries, rather, they respect morphological boundaries. To address NER in MRLs we then need to answer two fundamental questions, namely, what are the basic units to be labeled, and how can these units be detected and classified in realistic settings (i.e., where no gold morphology is available). We empirically investigate these questions on a novel NER benchmark, with parallel token- level and morpheme-level NER annotations, which we develop for Modern Hebrew, a morphologically rich-and-ambiguous language. Our results show that explicitly modeling morphological boundaries leads to improved NER performance, and that a novel hybrid architecture, in which NER precedes and prunes morphological decomposition, greatly outperforms the standard pipeline, where morphological decomposition strictly precedes NER, setting a new performance bar for both Hebrew NER and Hebrew morphological decomposition tasks.}", issn = {2307-387X}, doi = {10.1162/tacl_a_00404}, url = {https://doi.org/10.1162/tacl\_a\_00404}, eprint = {https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl\_a\_00404/1962472/tacl\_a\_00404.pdf}, }

FRGC-Morphs is a dataset of morphed faces selected from the publicly available FRGC dataset [1]. We created the database by selecting similar looking pairs of people, and made 3 types of morphs for each pair using the following morphing tools: OpenCV [2], FaceMorpher [3], StyleGAN 2 [3]. * [1] https://www.nist.gov/programs-projects/face-recognition-grand-challenge-frgc * [2] https://www.learnopencv.com/face-morph-using-opencv-cpp-python * [3] https://github.com/yaopang/FaceMorpher/tree/master/facemorpher * [4] https://github.com/NVlabs/stylegan2

The MHSMA dataset is a collection of human sperm images from 235 patients with male factor infertility. Each image is labeled by experts for normal or abnormal sperm acrosome, head, vacuole, and tail. The training, validation, and test sets contain 1000, 240, and 300 images, respectively. Images are available in two different crop sizes: 128x128- and 64x64-pixel. Paper: A novel deep learning method for automatic assessment of human sperm images

Morph Call is a suite of 46 probing tasks for four Indo-European languages that fall under different morphology: Russian, French, English, and German. The tasks are designed to explore the morphosyntactic content of multilingual transformers which is a less studied aspect at the moment. The tasks are divided into four groups: * Morphosyntactic Features: probe the encoder for the occurrence of the morphosyntactic properties. * Masked Token: analogous to Morphosyntactic Features with the exception that the target word is replaced with a tokenizer-specific mask token. * Morphosyntactic Values: is a group of k-way classification tasks for each feature where k is the number of values that the feature can take. * Perturbations: tasks test the encoder sensitivity to syntactic and inflectional sentence perturbations. ## Probing Methods * Supervised probing involves training a Logistic Regression classifier to predict a property. The performance is used as a proxy to evaluate the model knowledge. * Neuron-level Analysis [Durrani et al., 2020] allows retrieving a group of individual neurons that are most relevant to predict a linguistic property. * Contextual Correlation Analysis [Wu et al., 2020] is a representation-level similarity measure that allows identifying pairs of layers of similar behavior. ## Usage We provide an example of the experiment on Masked Token task (Case, German). bash me@my-laptop:~$ python3 probe.py --help INFO: Showing help with the command 'probe.py -- --help'. NAME probe.py - configure the experiment AND perform probing SYNOPSIS probe.py <flags> DESCRIPTION configure the experiment AND perform probing FLAGS --results_path=RESULTS_PATH Type: Optional[str] Default: None path to a folder to store the probing results and the model intermediate activations --model_architecture=MODEL_ARCHITECTURE Type: typ... Default: 'bert multilingual' --model_is_finetuned=MODEL_IS_FINETUNED Type: bool Default: False if to perform the experiment on the fine-tuned model --model_finetuned_path=MODEL_FINETUNED_PATH Type: Optional[str] Default: None (only if model_is_finetuned is True) path to store the fine-tuned model --model_finetuned_config_google_url=MODEL_FINETUNED_CONFIG_GOOGLE_URL Type: Optional[] Default: None (only if model_is_finetuned is True) the url of the fine-tuned model config if to be downloaded --model_finetuned_model_google_url=MODEL_FINETUNED_MODEL_GOOGLE_URL Type: Optional[] Default: None (only if model_is_finetuned is True) the url of the fine-tuned model weights if to be downloaded --model_is_random=MODEL_IS_RANDOM Type: bool Default: False if to perform the random initialization of the model --layers_to_probe=LAYERS_TO_PROBE Type: List Default: 'all' (either "all" or list w. possible numbers from 0 to 11) -- model layers to probe. e.g.: [1, 3, 11], or "all" --train_n_sentences=TRAIN_N_SENTENCES Type: int Default: 1500 number of sentences used to train the probing classifier --test_n_sentences=TEST_N_SENTENCES Type: int Default: 1000 number of sentences used to evaluate the probing classifier --dev_n_sentences=DEV_N_SENTENCES Type: int Default: 0 DEPRECATED

DLBCL-Morph is a dataset containing 42 digitally scanned high-resolution tissue microarray (TMA) slides accompanied by clinical, cytogenetic, and geometric features from 209 DLBCL cases. Source: https://github.com/stanfordmlgroup/DLBCL-Morph

The following experimental data were obtained on lithography devices made of magnetic multilayer tracks and thin tantalum transverse electrodes by Kerr microscopy and anomalous Hall effect measurements. The results, demonstrating the weighted sum operation using magnetic skyrmions, are published in T. da Câmara Santa Clara Gomes et al., Neuromorphic weighted sums with magnetic skyrmions, Nature Electronics (2024). Please find in the README additional information regarding the data files and the variables.

At the Isfahan Fertility and Infertility Center, semen samples were collected from fifteen patients. The sperm samples were fixed and stained using the Diff-Quick method. Using an Olympus CX21 microscope with a ×100 objective lens and a ×10 eyepiece and a Sony color camera (Model No SSC-DC58AP), 725 images were taken. The resolution of each image was 576×720 pixels. From these images, the sperm heads were cropped and classified into five classes by three specialists. The classes are Normal, Pyriform, Tapered, Amorphous, and Others. After the classification, only the samples which there was a collective consensus about their class were kept in the dataset. Four classes of Normal, Pyriform, Tapered, and Amorphous are included in this dataset. The resulting dataset of sperm heads denoted as Human Sperm Head Morphology dataset (HuSHeM) consists of four folders, each corresponding to a specific set of sperm shapes. The folder names reflect the shape of the contained images. There are 54 Normal, 53 Tapered, 57 Pyriform, and 52 Amorphous sperm heads. The images of sperm heads are in the RGB format with the size of 131×131 pixels.

Revealing latent structure in data is an active field of research, having introduced exciting technologies such as variational autoencoders and adversarial networks, and is essential to push machine learning towards unsupervised knowledge discovery. However, a major challenge is the lack of suitable benchmarks for an objective and quantitative evaluation of learned representations. To address this issue we introduce Morpho-MNIST, a framework that aims to answer: "to what extent has my model learned to represent specific factors of variation in the data?" We extend the popular MNIST dataset by adding a morphometric analysis enabling quantitative comparison of trained models, identification of the roles of latent variables, and characterisation of sample diversity. We further propose a set of quantifiable perturbations to assess the performance of unsupervised and supervised methods on challenging tasks such as outlier detection and domain adaptation. Data and code are available at https://github.com/dccastro/Morpho-MNIST.

Dataset can be used by anyone who is interested to perform morphological classification of galaxies. Originally dataset provided by Kaggle user Jay Lin (https://www.kaggle.com/jay1985) 4 years ago. Dataset was used in conference paper "Morphological Classification of Galaxies Using SpinalNet"

This dataset is for evaluation of morphosyntactic analyzers.

Data was acquired to investigate the effects of morphine withdrawal in rats, both in the brain neurochemistry and ultrasonic vocalisation. To this end, a following experiment was performed. 38 adult male Sprague–Dawley rats were used in the experiment, divided into four groups: Saline-Control (10), Morphine-Control (9), Saline-Withdrawal (10) and Morphine-Withdrawal (9). Morphine in dose 10.0 mg/kg (s.c.) was administered repeatedly to the morphine groups over a 14 day period; saline solution was administered repeatedly (1.0 ml/kg) to other groups in the same manner. Administration was performed in testing cages in a group of four animals. The testing room was situated in a remote part of the laboratory, and significantly different than home cage room, both in the lighting conditions and in the arrangement of spatial cues, which were constant throughout the whole experiment. All animals were kept for 30 min in the testing box after each saline or morphine injection. On day 14, Morph-Control group and control Saline-Control group were exposed to the context of drug administration, and the ultrasonic vocalizations were recorded for 20 min. Withdrawal groups, 30 min after last injection, were left undisturbed (in their home cages), whilst they were subjected to 2-week withdrawal period. On day 28, the rats were re-exposed to the context of morphine/saline administration and ultrasonic vocalization was recorded. Each rat was immediately decapitated after USVs recording session, and its brain tissues were frozen. The USVs were recorded individually for each rat, in a dark room with dim red light. USV recordings were processed using a proprietary RatRec Pro software; individual calls were extracted and counted. All identified episodes were of the "50 kHz appetitive" class, no "aversive 22 kHz" alarm calls were recorded. For each rat, tissue samples of 6 brain structures were extracted: medial prefrontal cortex (mPFC), nucleus accumbens (NAcc), striatum (Cpu), hippocampus (Hipp), amygdala and ventral tegmental area (VTA). In each sample, levels of 15 compounds were measured: norepinephrine (NA), 3-methoxy-4-hydroxyphenylglycol (MHPG), 3,4-dihydroxyphenylacetic acid (DOPAC), dopamine (DA), 5-hydroxyindoleacetic acid (5-HIAA), homovanillic acid (HVA), serotonin (5-HT), 3-methoxytyramine (3-MT), taurine, glutamine (Gln), glycine (Gly), aspartic acid (Asp), glutamic acid (Glu), alanine (Ala) and gamma-aminobutyric acid (GABA).

The data used in - "Radio Galaxy Zoo EMU: Towards a Semantic Radio Galaxy Morphology Taxonomy" (Bowles et al. submitted) - "A New Task: Deriving Semantic Class Targets for the Physical Sciences" (Bowles et al. 2022: https://arxiv.org/abs/2210.14760) accepted at the Fifth Workshop on Machine Learning and the Physical Sciences, Neural Information Processing Systems 2022. This data consists of images of galaxies, and plain English annotations of the features of the radio galaxies, as well as expert classifications using pre-existing scientific classes. Additionally the data presented contains checkpoints of the data at various stages throughout the processing initially completed with https://github.com/mb010/Text2Tag.

Dataset of sperm head images with expert-classification labels. The dataset contains 1854 sperm head images obtained from six semen smears and classified by three Chilean referent domain experts according to World Health Organization (WHO) criteria, in one of the following classes: normal, tapered, pyriform, small and amorphous. This gold-standard is aimed for use in evaluating and comparing not only known techniques, but also future improvements to present approaches for classification of human sperm heads for semen analysis.

TEM image dataset containing four nanowire morphologies of bio-derived protein nanowires and synthetic peptide nanowires. The peptide / protein nanowires used in this study were synthesized and imaged by Brian Montz in Prof. Todd Emrick's research group at the Department of Polymer Science and Engineering Department, University of Massachusetts Amherst. We acknowledge financial support from the U.S. National Science Foundation, Grant NSF DMREF #1921839 and DMREF #1921871. Nanowires were classified into either of the four morphologies: bundle, singular, dispersed or network. Each morphology contains 100 images (jpg files). For the dispersed and network morphologies, because these two morphologies are harder to visually distinguish, we have created manual segmentation labels of the nanowires (included in these two morphology folders as png files). Percolation analysis was done on these manually segmented nanowires to provide quantitative metric on whether the nanowires form a network in the image. encoders_trained_with_optimized_hyperparameter.zip contains 4 sets of encoders trained with either SimCLR or Barlow-Twins self-supervised methods on either generic TEM images, or generic everyday photographic images (each with 5 replicates with different random seed) with optimized hyperparameters. seg_mask_5_resolutions.zip contains ground truth 2D binary encoding of segmented nanowires at 5 resolutions.

Data for the paper entitled Quantifying yeast colony morphologies with feature engineering from time-lapse photography by A. Goldschmidt et al. (https://arxiv.org/abs/2201.05259) This project is a collaboration between Dudley Lab at the Pacific NW Research Institute and the J. Nathan Kutz group at the University of Washington. Summary: Baker's yeast (Saccharomyces cerevisiae) is a model organism for studying the morphology that emerges at the scale of multi-cell colonies. To look at how morphology develops, we collect a dataset of time-lapse photographs of the growth of different strains of S. cerevisiae.

Mac-Morpho is a corpus of Brazilian Portuguese texts annotated with part-of-speech tags. Its first version was released in 2003 [1], and since then, two revisions have been made in order to improve the quality of the resource [2, 3]. The corpus is available for download split into train, development and test sections. These are 76%, 4% and 20% of the corpus total, respectively (the reason for the unusual numbers is that the corpus was first split into 80%/20% train/test, and then 5% of the train section was set aside for development). This split was used in [3], and new POS tagging research with Mac-Morpho is encouraged to follow it in order to make consistent comparisons possible.