The CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The images are labelled with one of 10 mutually exclusive classes: airplane, automobile (but not truck or pickup truck), bird, cat, deer, dog, frog, horse, ship, and truck (but not pickup truck). There are 6000 images per class with 5000 training and 1000 testing images per class.

12,840 PAPERS • 72 BENCHMARKS

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.

12,401 PAPERS • 113 BENCHMARKS

The MS COCO (Microsoft Common Objects in Context) dataset is a large-scale object detection, segmentation, key-point detection, and captioning dataset. The dataset consists of 328K images.

9,057 PAPERS • 85 BENCHMARKS

The CIFAR-100 dataset (Canadian Institute for Advanced Research, 100 classes) is a subset of the Tiny Images dataset and consists of 60000 32x32 color images. The 100 classes in the CIFAR-100 are grouped into 20 superclasses. There are 600 images per class. Each image comes with a "fine" label (the class to which it belongs) and a "coarse" label (the superclass to which it belongs). There are 500 training images and 100 testing images per class.

6,802 PAPERS • 48 BENCHMARKS

The MNIST database (Modified National Institute of Standards and Technology database) is a large collection of handwritten digits. It has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger NIST Special Database 3 (digits written by employees of the United States Census Bureau) and Special Database 1 (digits written by high school students) which contain monochrome images of handwritten digits. The digits have been size-normalized and centered in a fixed-size image. The original black and white (bilevel) images from NIST were size normalized to fit in a 20x20 pixel box while preserving their aspect ratio. The resulting images contain grey levels as a result of the anti-aliasing technique used by the normalization algorithm. the images were centered in a 28x28 image by computing the center of mass of the pixels, and translating the image so as to position this point at the center of the 28x28 field.

6,637 PAPERS • 51 BENCHMARKS

Cityscapes is a large-scale database which focuses on semantic understanding of urban street scenes. It provides semantic, instance-wise, and dense pixel annotations for 30 classes grouped into 8 categories (flat surfaces, humans, vehicles, constructions, objects, nature, sky, and void). The dataset consists of around 5000 fine annotated images and 20000 coarse annotated ones. Data was captured in 50 cities during several months, daytimes, and good weather conditions. It was originally recorded as video so the frames were manually selected to have the following features: large number of dynamic objects, varying scene layout, and varying background.

3,043 PAPERS • 43 BENCHMARKS

KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) is one of the most popular datasets for use in mobile robotics and autonomous driving. It consists of hours of traffic scenarios recorded with a variety of sensor modalities, including high-resolution RGB, grayscale stereo cameras, and a 3D laser scanner. Despite its popularity, the dataset itself does not contain ground truth for semantic segmentation. However, various researchers have manually annotated parts of the dataset to fit their necessities. Álvarez et al. generated ground truth for 323 images from the road detection challenge with three classes: road, vertical, and sky. Zhang et al. annotated 252 (140 for training and 112 for testing) acquisitions – RGB and Velodyne scans – from the tracking challenge for ten object categories: building, sky, road, vegetation, sidewalk, car, pedestrian, cyclist, sign/pole, and fence. Ros et al. labeled 170 training images and 46 testing images (from the visual odome

2,974 PAPERS • 121 BENCHMARKS

Street View House Numbers (SVHN) is a digit classification benchmark dataset that contains 600,000 32×32 RGB images of printed digits (from 0 to 9) cropped from pictures of house number plates. The cropped images are centered in the digit of interest, but nearby digits and other distractors are kept in the image. SVHN has three sets: training, testing sets and an extra set with 530,000 images that are less difficult and can be used for helping with the training process.

2,887 PAPERS • 12 BENCHMARKS

CelebFaces Attributes dataset contains 202,599 face images of the size 178×218 from 10,177 celebrities, each annotated with 40 binary labels indicating facial attributes like hair color, gender and age.

2,837 PAPERS • 18 BENCHMARKS

Fashion-MNIST is a dataset comprising of 28×28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST shares the same image size, data format and the structure of training and testing splits with the original MNIST.

2,546 PAPERS • 18 BENCHMARKS

The Caltech-UCSD Birds-200-2011 (CUB-200-2011) dataset is the most widely-used dataset for fine-grained visual categorization task. It contains 11,788 images of 200 subcategories belonging to birds, 5,994 for training and 5,794 for testing. Each image has detailed annotations: 1 subcategory label, 15 part locations, 312 binary attributes and 1 bounding box. The textual information comes from Reed et al.. They expand the CUB-200-2011 dataset by collecting fine-grained natural language descriptions. Ten single-sentence descriptions are collected for each image. The natural language descriptions are collected through the Amazon Mechanical Turk (AMT) platform, and are required at least 10 words, without any information of subcategories and actions.

1,799 PAPERS • 42 BENCHMARKS

ShapeNet is a large scale repository for 3D CAD models developed by researchers from Stanford University, Princeton University and the Toyota Technological Institute at Chicago, USA. The repository contains over 300M models with 220,000 classified into 3,135 classes arranged using WordNet hypernym-hyponym relationships. ShapeNet Parts subset contains 31,693 meshes categorised into 16 common object classes (i.e. table, chair, plane etc.). Each shapes ground truth contains 2-5 parts (with a total of 50 part classes).

1,513 PAPERS • 11 BENCHMARKS

Visual Question Answering (VQA) is a dataset containing open-ended questions about images. These questions require an understanding of vision, language and commonsense knowledge to answer. The first version of the dataset was released in October 2015. VQA v2.0 was released in April 2017.

1,399 PAPERS • 2 BENCHMARKS

The nuScenes dataset is a large-scale autonomous driving dataset. The dataset has 3D bounding boxes for 1000 scenes collected in Boston and Singapore. Each scene is 20 seconds long and annotated at 2Hz. This results in a total of 28130 samples for training, 6019 samples for validation and 6008 samples for testing. The dataset has the full autonomous vehicle data suite: 32-beam LiDAR, 6 cameras and radars with complete 360° coverage. The 3D object detection challenge evaluates the performance on 10 classes: cars, trucks, buses, trailers, construction vehicles, pedestrians, motorcycles, bicycles, traffic cones and barriers.

1,253 PAPERS • 17 BENCHMARKS

Visual Genome contains Visual Question Answering data in a multi-choice setting. It consists of 101,174 images from MSCOCO with 1.7 million QA pairs, 17 questions per image on average. Compared to the Visual Question Answering dataset, Visual Genome represents a more balanced distribution over 6 question types: What, Where, When, Who, Why and How. The Visual Genome dataset also presents 108K images with densely annotated objects, attributes and relationships.

1,057 PAPERS • 19 BENCHMARKS

ScanNet is an instance-level indoor RGB-D dataset that includes both 2D and 3D data. It is a collection of labeled voxels rather than points or objects. Up to now, ScanNet v2, the newest version of ScanNet, has collected 1513 annotated scans with an approximate 90% surface coverage. In the semantic segmentation task, this dataset is marked in 20 classes of annotated 3D voxelized objects.

1,049 PAPERS • 16 BENCHMARKS

Flickr-Faces-HQ (FFHQ) consists of 70,000 high-quality PNG images at 1024×1024 resolution and contains considerable variation in terms of age, ethnicity and image background. It also has good coverage of accessories such as eyeglasses, sunglasses, hats, etc. The images were crawled from Flickr, thus inheriting all the biases of that website, and automatically aligned and cropped using dlib. Only images under permissive licenses were collected. Various automatic filters were used to prune the set, and finally Amazon Mechanical Turk was used to remove the occasional statues, paintings, or photos of photos.

1,038 PAPERS • 16 BENCHMARKS

The Places dataset is proposed for scene recognition and contains more than 2.5 million images covering more than 205 scene categories with more than 5,000 images per category.

955 PAPERS • 5 BENCHMARKS

The STL-10 is an image dataset derived from ImageNet and popularly used to evaluate algorithms of unsupervised feature learning or self-taught learning. Besides 100,000 unlabeled images, it contains 13,000 labeled images from 10 object classes (such as birds, cats, trucks), among which 5,000 images are partitioned for training while the remaining 8,000 images for testing. All the images are color images with 96×96 pixels in size.

882 PAPERS • 17 BENCHMARKS

Oxford 102 Flower is an image classification dataset consisting of 102 flower categories. The flowers chosen to be flower commonly occurring in the United Kingdom. Each class consists of between 40 and 258 images.

872 PAPERS • 6 BENCHMARKS

The ADE20K semantic segmentation dataset contains more than 20K scene-centric images exhaustively annotated with pixel-level objects and object parts labels. There are totally 150 semantic categories, which include stuffs like sky, road, grass, and discrete objects like person, car, bed.

850 PAPERS • 19 BENCHMARKS

Office-Home is a benchmark dataset for domain adaptation which contains 4 domains where each domain consists of 65 categories. The four domains are: Art – artistic images in the form of sketches, paintings, ornamentation, etc.; Clipart – collection of clipart images; Product – images of objects without a background and Real-World – images of objects captured with a regular camera. It contains 15,500 images, with an average of around 70 images per class and a maximum of 99 images in a class.

831 PAPERS • 11 BENCHMARKS

Market-1501 is a large-scale public benchmark dataset for person re-identification. It contains 1501 identities which are captured by six different cameras, and 32,668 pedestrian image bounding-boxes obtained using the Deformable Part Models pedestrian detector. Each person has 3.6 images on average at each viewpoint. The dataset is split into two parts: 750 identities are utilized for training and the remaining 751 identities are used for testing. In the official testing protocol 3,368 query images are selected as probe set to find the correct match across 19,732 reference gallery images.

783 PAPERS • 9 BENCHMARKS

Tiny ImageNet contains 100000 images of 200 classes (500 for each class) downsized to 64×64 colored images. Each class has 500 training images, 50 validation images and 50 test images.

779 PAPERS • 7 BENCHMARKS

The LFW dataset contains 13,233 images of faces collected from the web. This dataset consists of the 5749 identities with 1680 people with two or more images. In the standard LFW evaluation protocol the verification accuracies are reported on 6000 face pairs.

754 PAPERS • 12 BENCHMARKS

The Large-scale Scene Understanding (LSUN) challenge aims to provide a different benchmark for large-scale scene classification and understanding. The LSUN classification dataset contains 10 scene categories, such as dining room, bedroom, chicken, outdoor church, and so on. For training data, each category contains a huge number of images, ranging from around 120,000 to 3,000,000. The validation data includes 300 images, and the test data has 1000 images for each category.

725 PAPERS • 10 BENCHMARKS

The CelebA-HQ dataset is a high-quality version of CelebA that consists of 30,000 images at 1024×1024 resolution.

721 PAPERS • 12 BENCHMARKS

The Human3.6M dataset is one of the largest motion capture datasets, which consists of 3.6 million human poses and corresponding images captured by a high-speed motion capture system. There are 4 high-resolution progressive scan cameras to acquire video data at 50 Hz. The dataset contains activities by 11 professional actors in 17 scenarios: discussion, smoking, taking photo, talking on the phone, etc., as well as provides accurate 3D joint positions and high-resolution videos.

662 PAPERS • 16 BENCHMARKS

The Flickr30k dataset contains 31,000 images collected from Flickr, together with 5 reference sentences provided by human annotators.

638 PAPERS • 6 BENCHMARKS

BSD is a dataset used frequently for image denoising and super-resolution. Of the subdatasets, BSD100 is aclassical image dataset having 100 test images proposed by Martin et al.. The dataset is composed of a large variety of images ranging from natural images to object-specific such as plants, people, food etc. BSD100 is the testing set of the Berkeley segmentation dataset BSD300.

584 PAPERS • 46 BENCHMARKS

The Stanford Cars dataset consists of 196 classes of cars with a total of 16,185 images, taken from the rear. The data is divided into almost a 50-50 train/test split with 8,144 training images and 8,041 testing images. Categories are typically at the level of Make, Model, Year. The images are 360×240.

555 PAPERS • 9 BENCHMARKS

The Office dataset contains 31 object categories in three domains: Amazon, DSLR and Webcam. The 31 categories in the dataset consist of objects commonly encountered in office settings, such as keyboards, file cabinets, and laptops. The Amazon domain contains on average 90 images per class and 2817 images in total. As these images were captured from a website of online merchants, they are captured against clean background and at a unified scale. The DSLR domain contains 498 low-noise high resolution images (4288×2848). There are 5 objects per category. Each object was captured from different viewpoints on average 3 times. For Webcam, the 795 images of low resolution (640×480) exhibit significant noise and color as well as white balance artifacts.

551 PAPERS • 7 BENCHMARKS

CLEVR (Compositional Language and Elementary Visual Reasoning) is a synthetic Visual Question Answering dataset. It contains images of 3D-rendered objects; each image comes with a number of highly compositional questions that fall into different categories. Those categories fall into 5 classes of tasks: Exist, Count, Compare Integer, Query Attribute and Compare Attribute. The CLEVR dataset consists of: a training set of 70k images and 700k questions, a validation set of 15k images and 150k questions, a test set of 15k images and 150k questions about objects, answers, scene graphs and functional programs for all train and validation images and questions. Each object present in the scene, aside of position, is characterized by a set of four attributes: 2 sizes: large, small, 3 shapes: square, cylinder, sphere, 2 material types: rubber, metal, 8 color types: gray, blue, brown, yellow, red, green, purple, cyan, resulting in 96 unique combinations.

544 PAPERS • 2 BENCHMARKS

The Describable Textures Dataset (DTD) contains 5640 texture images in the wild. They are annotated with human-centric attributes inspired by the perceptual properties of textures.

519 PAPERS • 5 BENCHMARKS

DomainNet is a dataset of common objects in six different domain. All domains include 345 categories (classes) of objects such as Bracelet, plane, bird and cello. The domains include clipart: collection of clipart images; real: photos and real world images; sketch: sketches of specific objects; infograph: infographic images with specific object; painting artistic depictions of objects in the form of paintings and quickdraw: drawings of the worldwide players of game “Quick Draw!”.

513 PAPERS • 10 BENCHMARKS

PACS is an image dataset for domain generalization. It consists of four domains, namely Photo (1,670 images), Art Painting (2,048 images), Cartoon (2,344 images) and Sketch (3,929 images). Each domain contains seven categories.

499 PAPERS • 7 BENCHMARKS

The Caltech101 dataset contains images from 101 object categories (e.g., “helicopter”, “elephant” and “chair” etc.) and a background category that contains the images not from the 101 object categories. For each object category, there are about 40 to 800 images, while most classes have about 50 images. The resolution of the image is roughly about 300×200 pixels.

497 PAPERS • 6 BENCHMARKS

The dataset contains 400 human action classes, with at least 400 video clips for each action. Each clip lasts around 10s and is taken from a different YouTube video. The actions are human focussed and cover a broad range of classes including human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands.

492 PAPERS • NO BENCHMARKS YET

The Places205 dataset is a large-scale scene-centric dataset with 205 common scene categories. The training dataset contains around 2,500,000 images from these categories. In the training set, each scene category has the minimum 5,000 and maximum 15,000 images. The validation set contains 100 images per category (a total of 20,500 images), and the testing set includes 200 images per category (a total of 41,000 images).

491 PAPERS • 1 BENCHMARK

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.

473 PAPERS • 10 BENCHMARKS

DIV2K is a popular single-image super-resolution dataset which contains 1,000 images with different scenes and is splitted to 800 for training, 100 for validation and 100 for testing. It was collected for NTIRE2017 and NTIRE2018 Super-Resolution Challenges in order to encourage research on image super-resolution with more realistic degradation. This dataset contains low resolution images with different types of degradations. Apart from the standard bicubic downsampling, several types of degradations are considered in synthesizing low resolution images for different tracks of the challenges. Track 2 of NTIRE 2017 contains low resolution images with unknown x4 downscaling. Track 2 and track 4 of NTIRE 2018 correspond to realistic mild ×4 and realistic wild ×4 adverse conditions, respectively. Low-resolution images under realistic mild x4 setting suffer from motion blur, Poisson noise and pixel shifting. Degradations under realistic wild x4 setting are further extended to be of different

471 PAPERS • 3 BENCHMARKS

The Food-101 dataset consists of 101 food categories with 750 training and 250 test images per category, making a total of 101k images. The labels for the test images have been manually cleaned, while the training set contains some noise.

469 PAPERS • 11 BENCHMARKS

The Urban100 dataset contains 100 images of urban scenes. It commonly used as a test set to evaluate the performance of super-resolution models. Image Source: http://vllab.ucmerced.edu/wlai24/LapSRN/

458 PAPERS • 24 BENCHMARKS

The VGGFace2 dataset is made of around 3.31 million images divided into 9131 classes, each representing a different person identity. The dataset is divided into two splits, one for the training and one for test. The latter contains around 170000 images divided into 500 identities while all the other images belong to the remaining 8631 classes available for training. While constructing the datasets, the authors focused their efforts on reaching a very low label noise and a high pose and age diversity thus, making the VGGFace2 dataset a suitable choice to train state-of-the-art deep learning models on face-related tasks. The images of the training set have an average resolution of 137x180 pixels, with less than 1% at a resolution below 32 pixels (considering the shortest side).

456 PAPERS • 2 BENCHMARKS

VoxCeleb2 is a large scale speaker recognition dataset obtained automatically from open-source media. VoxCeleb2 consists of over a million utterances from over 6k speakers. Since the dataset is collected ‘in the wild’, the speech segments are corrupted with real world noise including laughter, cross-talk, channel effects, music and other sounds. The dataset is also multilingual, with speech from speakers of 145 different nationalities, covering a wide range of accents, ages, ethnicities and languages. The dataset is audio-visual, so is also useful for a number of other applications, for example – visual speech synthesis, speech separation, cross-modal transfer from face to voice or vice versa and training face recognition from video to complement existing face recognition datasets.

448 PAPERS • 5 BENCHMARKS

The MPII Human Pose Dataset for single person pose estimation is composed of about 25K images of which 15K are training samples, 3K are validation samples and 7K are testing samples (which labels are withheld by the authors). The images are taken from YouTube videos covering 410 different human activities and the poses are manually annotated with up to 16 body joints.

445 PAPERS • 4 BENCHMARKS

ImageNet-C is an open source data set that consists of algorithmically generated corruptions (blur, noise) applied to the ImageNet test-set.

434 PAPERS • 3 BENCHMARKS

The iNaturalist 2017 dataset (iNat) contains 675,170 training and validation images from 5,089 natural fine-grained categories. Those categories belong to 13 super-categories including Plantae (Plant), Insecta (Insect), Aves (Bird), Mammalia (Mammal), and so on. The iNat dataset is highly imbalanced with dramatically different number of images per category. For example, the largest super-category “Plantae (Plant)” has 196,613 images from 2,101 categories; whereas the smallest super-category “Protozoa” only has 381 images from 4 categories.

432 PAPERS • 10 BENCHMARKS