Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 11편

MAGE

MAGE 설명 보기

The MAGE dataset provides a large set of generated texts using 27 LLMs from seven different groups: OpenAI GPT, LLaMA, GLM130B, FLAN-T5, OPT, BigScience, and EleutherAI. In total, the dataset contains 432,682 texts, along with two additional sets. The first is an additional test set with texts from unseen domains generated by an unseen model, namely GPT-4. The second set is designed to evaluate the robustness of detectors against paraphrasing attacks. To achieve this, the GPT-3.5-turbo model was employed to paraphrase the sentences from the first set, with all paraphrased texts treated as machine-generated.

관련 논문 15,430편

ImageNet

ImageNet 설명 보기

The ImageNet dataset contains 14,197,122 annotated images according to the WordNet hierarchy. Since 2010 the dataset is used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC), a benchmark in image classification and object detection. The publicly released dataset contains a set of manually annotated training images. A set of test images is also released, with the manual annotations withheld. ILSVRC annotations fall into one of two categories: (1) image-level annotation of a binary label for the presence or absence of an object class in the image, e.g., “there are cars in this image” but “there are no tigers,” and (2) object-level annotation of a tight bounding box and class label around an object instance in the image, e.g., “there is a screwdriver centered at position (20,25) with width of 50 pixels and height of 30 pixels”. The ImageNet project does not own the copyright of the images, therefore only thumbnails and URLs of images are provided. * Total number of non-empty WordNet synsets: 21841 * Total number of images: 14197122 * Number of images with bounding box annotations: 1,034,908 * Number of synsets with SIFT features: 1000 * Number of images with SIFT features: 1.2 million Source: ImageNet Large Scale Visual Recognition Challenge Image Source: https://cs.stanford.edu/people/karpathy/cnnembed/

관련 논문 1,345편

mini-Imagenet

mini-Imagenet 설명 보기

mini-Imagenet is proposed by Matching Networks for One Shot Learning . In NeurIPS, 2016. This dataset consists of 50000 training images and 10000 testing images, evenly distributed across 100 classes.

관련 논문 538편

SYNTHetic Collection of Imagery and Annotations

SYNTHIA
SYNTHIA 설명 보기

The SYNTHIA dataset is a synthetic dataset that consists of 9400 multi-viewpoint photo-realistic frames rendered from a virtual city and comes with pixel-level semantic annotations for 13 classes. Each frame has resolution of 1280 × 960. Source: Orientation-aware Semantic Segmentation on Icosahedron Spheres Image Source: https://synthia-dataset.net/

관련 논문 481편

ImageNet-Rendition

ImageNet-R
ImageNet-R 설명 보기

ImageNet-R(endition) contains art, cartoons, deviantart, graffiti, embroidery, graphics, origami, paintings, patterns, plastic objects, plush objects, sculptures, sketches, tattoos, toys, and video game renditions of ImageNet classes. ImageNet-R has renditions of 200 ImageNet classes resulting in 30,000 images. Source: The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

관련 논문 317편

tieredImageNet

tieredImageNet 설명 보기

The tieredImageNet dataset is a larger subset of ILSVRC-12 with 608 classes (779,165 images) grouped into 34 higher-level nodes in the ImageNet human-curated hierarchy. This set of nodes is partitioned into 20, 6, and 8 disjoint sets of training, validation, and testing nodes, and the corresponding classes form the respective meta-sets. As argued in Ren et al. (2018), this split near the root of the ImageNet hierarchy results in a more challenging, yet realistic regime with test classes that are less similar to training classes. Source: tieredImageNet Image Source: https://arxiv.org/pdf/1803.00676.pdf

관련 논문 311편

Digital Retinal Images for Vessel Extraction

DRIVE
DRIVE 설명 보기

The Digital Retinal Images for Vessel Extraction (DRIVE) dataset is a dataset for retinal vessel segmentation. It consists of a total of JPEG 40 color fundus images; including 7 abnormal pathology cases. The images were obtained from a diabetic retinopathy screening program in the Netherlands. The images were acquired using Canon CR5 non-mydriatic 3CCD camera with FOV equals to 45 degrees. Each image resolution is 584*565 pixels with eight bits per color channel (3 channels). The set of 40 images was equally divided into 20 images for the training set and 20 images for the testing set. Inside both sets, for each image, there is circular field of view (FOV) mask of diameter that is approximately 540 pixels. Inside training set, for each image, one manual segmentation by an ophthalmological expert has been applied. Inside testing set, for each image, two manual segmentations have been applied by two different observers, where the first observer segmentation is accepted as the ground-truth for performance evaluation. Source: Ant Colony based Feature Selection Heuristics for Retinal Vessel Segmentation Image Source: https://drive.grand-challenge.org/

관련 논문 293편

Dataset for Object deTection in Aerial Images

DOTA
DOTA 설명 보기

DOTA is a large-scale dataset for object detection in aerial images. It can be used to develop and evaluate object detectors in aerial images. The images are collected from different sensors and platforms. Each image is of the size in the range from 800 × 800 to 20,000 × 20,000 pixels and contains objects exhibiting a wide variety of scales, orientations, and shapes. The instances in DOTA images are annotated by experts in aerial image interpretation by arbitrary (8 d.o.f.) quadrilateral. We will continue to update DOTA, to grow in size and scope to reflect evolving real-world conditions. Now it has three versions: DOTA-v1.0 contains 15 common categories, 2,806 images and 188, 282 instances. The proportions of the training set, validation set, and testing set in DOTA-v1.0 are 1/2, 1/6, and 1/3, respectively. DOTA-v1.5 uses the same images as DOTA-v1.0, but the extremely small instances (less than 10 pixels) are also annotated. Moreover, a new category, ”container crane” is added. It contains 403,318 instances in total. The number of images and dataset splits are the same as DOTA-v1.0. This version was released for the DOAI Challenge 2019 on Object Detection in Aerial Images in conjunction with IEEE CVPR 2019. DOTA-v2.0 collects more Google Earth, GF-2 Satellite, and aerial images. There are 18 common categories, 11,268 images and 1,793,658 instances in DOTA-v2.0. Compared to DOTA-v1.5, it further adds the new categories of ”airport” and ”helipad”. The 11,268 images of DOTA are split into training, validation, test-dev, and test-challenge sets. To avoid the problem of overfitting, the proportion of training and validation set is smaller than the test set. Furthermore, we have two test sets, namely test-dev and test-challenge. Training contains 1,830 images and 268,627 instances. Validation contains 593 images and 81,048 instances. We released the images and ground truths for training and validation sets. Test-dev contains 2,792 images and 353,346 instances. We released the images but not the ground truths. Test-challenge contains 6,053 images and 1,090,637 instances. Source: https://captain-whu.github.io/DOTA/index.html Image Source: https://captain-whu.github.io/DOTA/

관련 논문 268편

ImageNet-Sketch

ImageNet-Sketch 설명 보기

ImageNet-Sketch data set consists of 50,889 images, approximately 50 images for each of the 1000 ImageNet classes. The data set is constructed with Google Image queries "sketch of __", where __ is the standard class name. Only within the "black and white" color scheme is searched. 100 images are initially queried for every class, and the pulled images are cleaned by deleting the irrelevant images and images that are for similar but different classes. For some classes, there are less than 50 images after manually cleaning, and then the data set is augmented by flipping and rotating the images. Source: ImageNet-Sketch Image Source: https://github.com/HaohanWang/ImageNet-Sketch

관련 논문 245편

Smartphone Image Denoising Dataset

SIDD
SIDD 설명 보기

SIDD is an image denoising dataset containing 30,000 noisy images from 10 scenes under different lighting conditions using five representative smartphone cameras. Ground truth images are provided along with the noisy images. Source: A High-Quality Denoising Dataset for Smartphone Cameras

관련 논문 115편

Categorical Subjective Image Quality

CSIQ
CSIQ 설명 보기

The CSIQ database consists of 30 original images, each is distorted using six different types of distortions at four to five different levels of distortion. CSIQ images are subjectively rated base on a linear displacement of the images across four calibrated LCD monitors placed side by side with equal viewing distance to the observer. The database contains 5000 subjective ratings from 35 different observers, and ratings are reported in the form of DMOS.

관련 논문 113편

Konstanz Image Quality 10k Database

KonIQ-10k
KonIQ-10k 설명 보기

KonIQ-10k is a large-scale IQA dataset consisting of 10,073 quality scored images. This is the first in-the-wild database aiming for ecological validity, with regard to the authenticity of distortions, the diversity of content, and quality-related indicators. Through the use of crowdsourcing, we obtained 1.2 million reliable quality ratings from 1,459 crowd workers, paving the way for more general IQA models.

관련 논문 112편

Gland Segmentation in Colon Histology Images Challenge

GlaS
GlaS 설명 보기

The dataset used in this challenge consists of 165 images derived from 16 H&E stained histological sections of stage T3 or T42 colorectal adenocarcinoma. Each section belongs to a different patient, and sections were processed in the laboratory on different occasions. Thus, the dataset exhibits high inter-subject variability in both stain distribution and tissue architecture. The digitization of these histological sections into whole-slide images (WSIs) was accomplished using a Zeiss MIRAX MIDI Slide Scanner with a pixel resolution of 0.465µm. Source: Sirinukunwattana et al. Image source: Sirinukunwattana et al.

관련 논문 106편

Stylized ImageNet

Stylized ImageNet 설명 보기

The Stylized-ImageNet dataset is created by removing local texture cues in ImageNet while retaining global shape information on natural images via AdaIN style transfer. This nudges CNNs towards learning more about shapes and less about local textures. Source: Adversarial Examples Improve Image Recognition Image Source: https://github.com/rgeirhos/Stylized-ImageNet

관련 논문 96편

ImageCLEF-DA

ImageCLEF-DA 설명 보기

The ImageCLEF-DA dataset is a benchmark dataset for ImageCLEF 2014 domain adaptation challenge, which contains three domains: Caltech-256 (C), ImageNet ILSVRC 2012 (I) and Pascal VOC 2012 (P). For each domain, there are 12 categories and 50 images in each category. Source: Domain-Symmetric Networks for Adversarial Domain Adaptation Image Source: https://www.imageclef.org/2014/adaptation

관련 논문 89편

ImageNet-O

ImageNet-O 설명 보기

ImageNet-O consists of images from classes that are not found in the ImageNet-1k dataset. It is used to test the robustness of vision models to out-of-distribution samples. It's reported using the AUPR metric.

관련 논문 87편

Underwater Image Enhancement Benchmark Dataset

UIEB
UIEB 설명 보기

Includes 950 real-world underwater images, 890 of which have the corresponding reference images. Source: An Underwater Image Enhancement Benchmark Dataset and Beyond

관련 논문 79편

Wikipedia-based Image Text

WIT
WIT 설명 보기

Wikipedia-based Image Text (WIT) Dataset is a large multimodal multilingual dataset. WIT is composed of a curated set of 37.6 million entity rich image-text examples with 11.5 million unique images across 108 Wikipedia languages. Its size enables WIT to be used as a pretraining dataset for multimodal machine learning models. Key Advantages A few unique advantages of WIT: - The largest multimodal dataset (time of this writing) by the number of image-text examples. - A massively multilingual (first of its kind) with coverage for over 100+ languages. - A collection of diverse set of concepts and real world entities. - Brings forth challenging real-world test sets.

관련 논문 70편

Remote Sensing Image Captioning Dataset

RSICD
RSICD 설명 보기

The Remote Sensing Image Captioning Dataset (RSICD) is a dataset for remote sensing image captioning task. It contains more than ten thousands remote sensing images which are collected from Google Earth, Baidu Map, MapABC and Tianditu. The images are fixed to 224X224 pixels with various resolutions. The total number of remote sensing images is 10921, with five sentences descriptions per image. Source: https://github.com/201528014227051/RSICD_optimal Image Source: https://github.com/201528014227051/RSICD_optimal

관련 논문 61편

Compose Image Retrieval on Real-life images

CIRR
CIRR 설명 보기

Composed Image Retrieval (or, Image Retreival conditioned on Language Feedback) is a relatively new retrieval task, where an input query consists of an image and short textual description of how to modify the image. For humans, the advantage of a bi-modal query is clear: some concepts and attributes are more succinctly described visually, others through language. By cross-referencing the two modalities, a reference image can capture the general gist of a scene, while the text can specify finer details. We identify a major challenge of this task as the inherent ambiguity in knowing what information is important (typically one object of interest in the scene) and what can be ignored (e.g., the background and other irrelevant objects). We release the first dataset of open-domain, real-life images with human-generated modification sentences, which support research on one-shot composed image retrieval, dialogue systems, fine-grained visiolinguistic reasoning, and more.

관련 논문 55편

Tiny-ImageNet-C

Tiny-ImageNet-C 설명 보기

Tiny ImageNet-C is an open-source data set comprising algorithmically generated corruptions applied to the Tiny ImageNet (ImageNet-200) test set comprising 200 classes following the concept of ImageNet-C. It was introduced by Hendrycks et al. ("Benchmarking Neural Network Robustness to Common Corruptions and Perturbations") and comprises 19 different corruptions (15 test corruptions and 4 validation corruptions) spanning 5 severity levels. This results in 200,000 images for the validation set and 750,000 images for the test set. For further information visit the original GitHub repository of ImageNet-C.

관련 논문 49편

2018 Data Science Bowl Find the nuclei in divergent images to advance medical discovery

2018 Data Science Bowl
2018 Data Science Bowl 설명 보기

This dataset contains a large number of segmented nuclei images. The images were acquired under a variety of conditions and vary in the cell type, magnification, and imaging modality (brightfield vs. fluorescence). The dataset is designed to challenge an algorithm's ability to generalize across these variations. Each image is represented by an associated ImageId. Files belonging to an image are contained in a folder with this ImageId. Within this folder are two subfolders: images contains the image file. masks contains the segmented masks of each nucleus. This folder is only included in the training set. Each mask contains one nucleus. Masks are not allowed to overlap (no pixel belongs to two masks). The second stage dataset will contain images from unseen experimental conditions. To deter hand labeling, it will also contain images that are ignored in scoring. The metric used to score this competition requires that your submissions are in run-length encoded format. Please see the evaluation page for details. As with any human-annotated dataset, you may find various forms of errors in the data. You may manually correct errors you find in the training set. The dataset will not be updated/re-released unless it is determined that there are a large number of systematic errors. The masks of the stage 1 test set will be released with the release of the stage 2 test set.

관련 논문 43편

ImageNet Semantic Segmentation

ImageNet-S
ImageNet-S 설명 보기

Powered by the ImageNet dataset, unsupervised learning on large-scale data has made significant advances for classification tasks. There are two major challenges to allowing such an attractive learning modality for segmentation tasks: i) a large-scale benchmark for assessing algorithms is missing; ii) unsupervised shape representation learning is difficult. We propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to track the research progress. Based on the ImageNet dataset, we propose the ImageNet-S dataset with 1.2 million training images and 50k high-quality semantic segmentation annotations for evaluation. Our benchmark has a high data diversity and a clear task objective. We also present a simple yet effective baseline method that works surprisingly well for LUSS. In addition, we benchmark related un/weakly/fully supervised methods accordingly, identifying the challenges and possible directions of LUSS.

관련 논문 40편

Aerial Image Dataset

AID
AID 설명 보기

AID is a new large-scale aerial image dataset, by collecting sample images from Google Earth imagery. Note that although the Google Earth images are post-processed using RGB renderings from the original optical aerial images, it has proven that there is no significant difference between the Google Earth images with the real optical aerial images even in the pixel-level land use/cover mapping. Thus, the Google Earth images can also be used as aerial images for evaluating scene classification algorithms. The new dataset is made up of the following 30 aerial scene types: airport, bare land, baseball field, beach, bridge, center, church, commercial, dense residential, desert, farmland, forest, industrial, meadow, medium residential, mountain, park, parking, playground, pond, port, railway station, resort, river, school, sparse residential, square, stadium, storage tanks and viaduct. All the images are labelled by the specialists in the field of remote sensing image interpretation, and some samples of each class are shown in Fig.1. In all, the AID dataset has a number of 10000 images within 30 classes. The images in AID are actually multi-source, as Google Earth images are from different remote imaging sensors. This brings more challenges for scene classification than the single source images like UC-Merced dataset. Moreover, all the sample images per each class in AID are carefully chosen from different countries and regions around the world, mainly in China, the United States, England, France, Italy, Japan, Germany, etc., and they are extracted at different time and seasons under different imaging conditions, which increases the intra-class diversities of the data.

관련 논문 39편

Dichotomous Image Segmentation (DIS) Dataset

DIS5K
DIS5K 설명 보기

To build the highly accurate Dichotomous Image Segmentation dataset (DIS5K), we first manually collected over 12,000 images from Flickr1 based on our pre-designed keywords. Then, we obtained 5,470 images of 22 groups and 225 categories from the 12,000 images according to the structural complexities of the objects. Each image is then manually labeled with pixel-wise accuracy using GIMP. The labeled targets in DIS5K mainly focus on the “objects of the images defined by the pre-designed keywords (categories)” regardless of their characteristics e.g., salient, common, camouflaged, meticulous, etc. The average per-image labeling time is ∼30 minutes and some images cost up to 10 hours.

관련 논문 39편

Task Directed Image Understanding Challenge

TDIUC
TDIUC 설명 보기

Task Directed Image Understanding Challenge (TDIUC) dataset is a Visual Question Answering dataset which consists of 1.6M questions and 170K images sourced from MS COCO and the Visual Genome Dataset. The image-question pairs are split into 12 categories and 4 additional evaluation matrices which help evaluate models’ robustness against answer imbalance and its ability to answer questions that require higher reasoning capability. The TDIUC dataset divides the VQA paradigm into 12 different task directed question types. These include questions that require a simpler task (e.g., object presence, color attribute) and more complex tasks (e.g., counting, positional reasoning). The dataset includes also an “Absurd” question category in which questions are irrelevant to the image contents to help balance the dataset. Source: Question-Agnostic Attention for Visual Question Answering Image Source: https://kushalkafle.com/projects/tdiuc.html

관련 논문 37편

Open Images V4

Open Images V4 설명 보기

Open Images V4 offers large scale across several dimensions: 30.1M image-level labels for 19.8k concepts, 15.4M bounding boxes for 600 object classes, and 375k visual relationship annotations involving 57 classes. For object detection in particular, 15x more bounding boxes than the next largest datasets (15.4M boxes on 1.9M images) are provided. The images often show complex scenes with several objects (8 annotated objects per image on average). Visual relationships between them are annotated, which support visual relationship detection, an emerging task that requires structured reasoning. Source: The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale Image Source: https://storage.googleapis.com/openimages/web/index.html

관련 논문 37편

Perceptual Image Processing ALgorithms IQA Dataset

PIPAL
PIPAL 설명 보기

PIPAL training set contains 200 reference images, 40 distortion types, 23k distortion images, and more than one million human ratings. Especially, we include GAN-based algorithms’ outputs as a new GAN-based distortion type. We employ the Elo rating system to assign the Mean Opinion Scores (MOS).

관련 논문 36편

Diverse Real-world image Super-Resolution

DRealSR
DRealSR 설명 보기

DRealSR establishes a Super Resolution (SR) benchmark with diverse real-world degradation processes, mitigating the limitations of conventional simulated image degradation. It has been collected from five DSLR cameras in natural scenes and cover indoor and outdoor scenes avoiding moving objects, e.g., advertising posters, plants, offices, buildings. The training images are cropped into 380×380, 272×272 and 192×192 patches, resulting in 31,970 patches. Source: Component Divide-and-Conquer for Real-World Image Super-Resolution

관련 논문 36편

Large Scale Underwater Image Dataset

LSUI
LSUI 설명 보기

We released a large-scale underwater image (LSUI) dataset including 5004 image pairs, which involve richer underwater scenes (lighting conditions, water types and target categories) and better visual quality reference images than the existing ones.

관련 논문 36편

VisualMRC: Machine Reading Comprehension on Document Images

VisualMRC
VisualMRC 설명 보기

VisualMRC is a visual machine reading comprehension dataset that proposes a task: given a question and a document image, a model produces an abstractive answer. You can find more details, analyses, and baseline results in the paper, VisualMRC: Machine Reading Comprehension on Document Images, AAAI 2021. Statistics: 10,197 images 30,562 QA pairs 10.53 average question tokens (tokenizing with NLTK tokenizer) 9.53 average answer tokens (tokenizing wit NLTK tokenizer) 151.46 average OCR tokens (tokenizing with NLTK tokenizer)

관련 논문 35편

Composed Image Retrieval on Common Objects in context

CIRCO
CIRCO 설명 보기

CIRCO (Composed Image Retrieval on Common Objects in context) is an open-domain benchmarking dataset for Composed Image Retrieval (CIR) based on real-world images from COCO 2017 unlabeled set. It is the first CIR dataset with multiple ground truths and aims to address the problem of false negatives in existing datasets. CIRCO comprises a total of 1020 queries, randomly divided into 220 and 800 for the validation and test set, respectively, with an average of 4.53 ground truths per query. Source: Zero-Shot Composed Image Retrieval with Textual Inversion Image Source: Zero-Shot Composed Image Retrieval with Textual Inversion

관련 논문 35편

COVID-19 Image Data Collection

COVID-19 Image Data Collection 설명 보기

Contains hundreds of frontal view X-rays and is the largest public resource for COVID-19 image and prognostic data, making it a necessary resource to develop and evaluate tools to aid in the treatment of COVID-19. Source: COVID-19 Image Data Collection

관련 논문 34편

Independent benchmark images and matched scans v1

IBims-1
IBims-1 설명 보기

iBims-1 (independent Benchmark images and matched scans - version 1) is a new high-quality RGB-D dataset, especially designed for testing single-image depth estimation (SIDE) methods. A customized acquisition setup, composed of a digital single-lens reflex (DSLR) camera and a high-precision laser scanner was used to acquire high-resolution images and highly accurate depth maps of diverse indoors scenarios. Compared to related RGB-D datasets, iBims-1 stands out due to a very low noise level, sharp depth transitions, no occlusions, and high depth ranges. Our dataset consists of the following components: Core dataset: - 100 RGB-D image pairs of various indoor scenes in high- and low resolution - Masks for invalid, transparent and planar regions (tables, floors, walls) - Masks for distinct depth transitions - Camera calibration parameters Auxiliary dataset: - 56 different color and geometric augmentations for each image of the core dataset - Additional hand-held images for testing MVS methods - Images of printed patterns and photos posted on a wall to assess performance of textured planar surfaces - Several RGB-D image sequences of static scenes with varying illumation Source: Evaluation of CNN-based Single-Image Depth Estimation Methods Image source: https://arxiv.org/pdf/1805.01328v1.pdf

관련 논문 34편

Segmentation of Underwater IMagery

SUIM
SUIM 설명 보기

The Segmentation of Underwater IMagery (SUIM) dataset contains over 1500 images with pixel annotations for eight object categories: fish (vertebrates), reefs (invertebrates), aquatic plants, wrecks/ruins, human divers, robots, and sea-floor. The images have been rigorously collected during oceanic explorations and human-robot collaborative experiments, and annotated by human participants. Source: Semantic Segmentation of Underwater Imagery: Dataset and Benchmark Image Source: http://irvlab.cs.umn.edu/resources/suim-dataset

관련 논문 32편

ImageNet-P

ImageNet-P 설명 보기

ImageNet-P consists of noise, blur, weather, and digital distortions. The dataset has validation perturbations; has difficulty levels; has CIFAR-10, Tiny ImageNet, ImageNet 64 × 64, standard, and Inception-sized editions; and has been designed for benchmarking not training networks. ImageNet-P departs from ImageNet-C by having perturbation sequences generated from each ImageNet validation image. Each sequence contains more than 30 frames, so to counteract an increase in dataset size and evaluation time only 10 common perturbations are used. Source: Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

관련 논문 32편

Perceptual Image Restoration and Manipulation

PIRM
PIRM 설명 보기

The PIRM dataset consists of 200 images, which are divided into two equal sets for validation and testing. These images cover diverse contents, including people, objects, environments, flora, natural scenery, etc. Images vary in size, and are typically ~300K pixels in resolution.

관련 논문 31편

Image-Grounded Language Understanding Evaluation

IGLUE
IGLUE 설명 보기

The Image-Grounded Language Understanding Evaluation (IGLUE) benchmark brings together—by both aggregating pre-existing datasets and creating new ones—visual question answering, cross-modal retrieval, grounded reasoning, and grounded entailment tasks across 20 diverse languages. The benchmark enables the evaluation of multilingual multimodal models for transfer learning, not only in a zero-shot setting, but also in newly defined few-shot learning setups.

관련 논문 31편

Image Paragraph Captioning

Image Paragraph Captioning 설명 보기

The Image Paragraph Captioning dataset allows researchers to benchmark their progress in generating paragraphs that tell a story about an image. The dataset contains 19,561 images from the Visual Genome dataset. Each image contains one paragraph. The training/val/test sets contains 14,575/2,487/2,489 images. Since all the images are also part of the Visual Genome dataset, each image also contains 50 region descriptions (short phrases describing parts of an image), 35 objects, 26 attributes and 21 relationships and 17 question-answer pairs. Source: A Hierarchical Approach for Generating Descriptive Image Paragraphs Image Source: https://cs.stanford.edu/people/ranjaykrishna/im2p/index.html

관련 논문 31편

Image-Chat

Image-Chat 설명 보기

The IMAGE-CHAT dataset is a large collection of (image, style trait for speaker A, style trait for speaker B, dialogue between A & B) tuples that we collected using crowd-workers, Each dialogue consists of consecutive turns by speaker A and B. No particular constraints are placed on the kinds of utterance, only that we ask the speakers to both use the provided style trait, and to respond to the given image and dialogue history in an engaging way. The goal is not just to build a diagnostic dataset but a basis for training models that humans actually want to engage with.