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.
14,953 PAPERS • 106 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.
14,226 PAPERS • 43 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.
8,230 PAPERS • 56 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.
7,233 PAPERS • 52 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.
1,153 PAPERS • 17 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.
1,029 PAPERS • 18 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.
725 PAPERS • 7 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.
706 PAPERS • 13 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.
674 PAPERS • 13 BENCHMARKS
FGVC-Aircraft contains 10,200 images of aircraft, with 100 images for each of 102 different aircraft model variants, most of which are airplanes. The (main) aircraft in each image is annotated with a tight bounding box and a hierarchical airplane model label. Aircraft models are organized in a four-levels hierarchy. The four levels, from finer to coarser, are:
461 PAPERS • 11 BENCHMARKS
NAS-Bench-201 is a benchmark (and search space) for neural architecture search. Each architecture consists of a predefined skeleton with a stack of the searched cell. In this way, architecture search is transformed into the problem of searching a good cell.
248 PAPERS • 4 BENCHMARKS
The LIDC-IDRI dataset contains lesion annotations from four experienced thoracic radiologists. LIDC-IDRI contains 1,018 low-dose lung CTs from 1010 lung patients.
219 PAPERS • 6 BENCHMARKS
CINIC-10 is a dataset for image classification. It has a total of 270,000 images, 4.5 times that of CIFAR-10. It is constructed from two different sources: ImageNet and CIFAR-10. Specifically, it was compiled as a bridge between CIFAR-10 and ImageNet. It is split into three equal subsets - train, validation, and test - each of which contain 90,000 images.
172 PAPERS • 3 BENCHMARKS
NAS-Bench-101 is the first public architecture dataset for NAS research. To build NASBench-101, the authors carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. The authors trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the precomputed dataset.
143 PAPERS • 1 BENCHMARK
The Oxford-IIIT Pet Dataset has 37 categories with roughly 200 images for each class. The images have a large variations in scale, pose and lighting. All images have an associated ground truth annotation of breed, head ROI, and pixel level trimap segmentation.
73 PAPERS • 5 BENCHMARKS
The Oxford-IIIT Pet Dataset is a 37-category pet dataset with roughly 200 images for each class. The images have large variations in scale, pose, and lighting. All images have an associated ground truth annotation of breed, head ROI, and pixel-level trimap segmentation.
46 PAPERS • 10 BENCHMARKS
A unified benchmark on searching for both topology and size, for (almost) any up-to-date NAS algorithm. NATS-Bench includes the search space of 15,625 neural cell candidates for architecture topology and 32,768 for architecture size on three datasets.
39 PAPERS • 6 BENCHMARKS
Visual Wake Words represents a common microcontroller vision use-case of identifying whether a person is present in the image or not, and provides a realistic benchmark for tiny vision models.
32 PAPERS • 2 BENCHMARKS
NAS-Bench-1Shot1 draws on the recent large-scale tabular benchmark NAS-Bench-101 for cheap anytime evaluations of one-shot NAS methods.
23 PAPERS • NO BENCHMARKS YET
MIR-1K (Multimedia Information Retrieval lab, 1000 song clips) is a dataset designed for singing voice separation. It contains:
20 PAPERS • NO BENCHMARKS YET
TransNAS-Bench-101 is a Neural Architecture Search (NAS) benchmark dataset containing network performance across seven tasks, covering classification, regression, pixel-level prediction, and self-supervised tasks. This diversity provides opportunities to transfer NAS methods among tasks and allows for more complex transfer schemes to evolve. We explore two fundamentally different types of search space: cell-level search space and macro-level search space. With 7,352 backbones evaluated on seven tasks, 51,464 trained models with detailed training information are provided. With TransNAS-Bench-101, we hope to encourage the advent of exceptional NAS algorithms that raise cross-task search efficiency and generalizability to the next level.
15 PAPERS • NO BENCHMARKS YET
Dataset for multi-target classification of five commonly appearing concrete defects.
9 PAPERS • NO BENCHMARKS YET
Freiburg Groceries is a groceries classification dataset consisting of 5000 images of size 256x256, divided into 25 categories. It has imbalanced class sizes ranging from 97 to 370 images per class. Images were taken in various aspect ratios and padded to squares.
7 PAPERS • NO BENCHMARKS YET
FarsBase-KBP contains 22015 sentences, in which the entities and relation types are linked to the FarsBase ontology. This gold dataset can be reused for benchmarking KBP systems in the Persian language.
2 PAPERS • NO BENCHMARKS YET
We present the first large-scale energy-aware benchmark that allows studying AutoML methods to achieve better trade-offs between performance and search energy consumption, named EA-HAS-Bench. EA-HAS-Bench provides a large-scale architecture/hyperparameter joint search space, covering diversified configurations related to energy consumption. Furthermore, we propose a novel surrogate model specially designed for large joint search space, which proposes a Bezier curve-based model to predict learning curves with unlimited shape and length.
1 PAPER • NO BENCHMARKS YET
HW-NAS-Bench is a dataset for HardWare-aware Neural Architecture Search (HW-NAS). It is the first dataset for HW-NAS research aiming to democratize HW-NAS research to non-hardware experts and facilitate a unified benchmark for HW-NAS to make HW-NAS research more reproducible and accessible, covering two SOTA NAS search spaces including NAS-Bench-201 and FBNet
Involves data where a robot interacts with 5.1 cm colored blocks to complete an order-fulfillment style block stacking task. It contains dynamic scenes and real time-series data in a less constrained environment than comparable datasets. There are nearly 12,000 stacking attempts and over 2 million frames of real data.