Science Question Answering (ScienceQA) is a new benchmark that consists of 21,208 multimodal multiple choice questions with diverse science topics and annotations of their answers with corresponding lectures and explanations. Out of the questions in ScienceQA, 10,332 (48.7%) have an image context, 10,220 (48.2%) have a text context, and 6,532 (30.8%) have both. Most questions are annotated with grounded lectures (83.9%) and detailed explanations (90.5%). The lecture and explanation provide general external knowledge and specific reasons, respectively, for arriving at the correct answer. To the best of our knowledge, ScienceQA is the first large-scale multimodal dataset that annotates lectures and explanations for the answers.
128 PAPERS • 1 BENCHMARK
The 2D-3D-S dataset provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. It covers over 6,000 m2 collected in 6 large-scale indoor areas that originate from 3 different buildings. It contains over 70,000 RGB images, along with the corresponding depths, surface normals, semantic annotations, global XYZ images (all in forms of both regular and 360° equirectangular images) as well as camera information. It also includes registered raw and semantically annotated 3D meshes and point clouds. The dataset enables development of joint and cross-modal learning models and potentially unsupervised approaches utilizing the regularities present in large-scale indoor spaces.
127 PAPERS • 8 BENCHMARKS
The Labeled Face Parts in-the-Wild (LFPW) consists of 1,432 faces from images downloaded from the web using simple text queries on sites such as google.com, flickr.com, and yahoo.com. Each image was labeled by three MTurk workers, and 29 fiducial points, shown below, are included in dataset.
127 PAPERS • NO BENCHMARKS YET
The STARE (Structured Analysis of the Retina) dataset is a dataset for retinal vessel segmentation. It contains 20 equal-sized (700×605) color fundus images. For each image, two groups of annotations are provided..
127 PAPERS • 7 BENCHMARKS
LAION-400M is a dataset with CLIP-filtered 400 million image-text pairs, their CLIP embeddings and kNN indices that allow efficient similarity search.
125 PAPERS • 1 BENCHMARK
LAION 5B is a large-scale dataset for research purposes consisting of 5,85B CLIP-filtered image-text pairs. 2,3B contain English language, 2,2B samples from 100+ other languages and 1B samples have texts that do not allow a certain language assignment (e.g. names ). Additionally, we provide several nearest neighbor indices, an improved web interface for exploration & subset creation as well as detection scores for watermark and NSFW.
125 PAPERS • NO BENCHMARKS YET
ObjectNet is a test set of images collected directly using crowd-sourcing. ObjectNet is unique as the objects are captured at unusual poses in cluttered, natural scenes, which can severely degrade recognition performance. There are 50,000 images in the test set which controls for rotation, background and viewpoint. There are 313 object classes with 113 overlapping ImageNet.
125 PAPERS • 4 BENCHMARKS
Objects365 is a large-scale object detection dataset, Objects365, which has 365 object categories over 600K training images. More than 10 million, high-quality bounding boxes are manually labeled through a three-step, carefully designed annotation pipeline. It is the largest object detection dataset (with full annotation) so far and establishes a more challenging benchmark for the community.
125 PAPERS • 3 BENCHMARKS
The Semantic Boundaries Dataset (SBD) is a dataset for predicting pixels on the boundary of the object (as opposed to the inside of the object with semantic segmentation). The dataset consists of 11318 images from the trainval set of the PASCAL VOC2011 challenge, divided into 8498 training and 2820 test images. This dataset has object instance boundaries with accurate figure/ground masks that are also labeled with one of 20 Pascal VOC classes.
The FC100 dataset (Fewshot-CIFAR100) is a newly split dataset based on CIFAR-100 for few-shot learning. It contains 20 high-level categories which are divided into 12, 4, 4 categories for training, validation and test. There are 60, 20, 20 low-level classes in the corresponding split containing 600 images of size 32 × 32 per class. Smaller image size makes it more challenging for few-shot learning.
123 PAPERS • 5 BENCHMARKS
The ORL Database of Faces contains 400 images from 40 distinct subjects. For some subjects, the images were taken at different times, varying the lighting, facial expressions (open / closed eyes, smiling / not smiling) and facial details (glasses / no glasses). All the images were taken against a dark homogeneous background with the subjects in an upright, frontal position (with tolerance for some side movement). The size of each image is 92x112 pixels, with 256 grey levels per pixel.
123 PAPERS • 1 BENCHMARK
The Replay-Attack Database for face spoofing consists of 1300 video clips of photo and video attack attempts to 50 clients, under different lighting conditions. All videos are generated by either having a (real) client trying to access a laptop through a built-in webcam or by displaying a photo or a video recording of the same client for at least 9 seconds.
VOT2018 is a dataset for visual object tracking. It consists of 60 challenging videos collected from real-life datasets.
The Make3D dataset is a monocular Depth Estimation dataset that contains 400 single training RGB and depth map pairs, and 134 test samples. The RGB images have high resolution, while the depth maps are provided at low resolution.
122 PAPERS • 1 BENCHMARK
The SumMe dataset is a video summarization dataset consisting of 25 videos, each annotated with at least 15 human summaries (390 in total).
120 PAPERS • 3 BENCHMARKS
PASCAL VOC 2007 is a dataset for image recognition. The twenty object classes that have been selected are:
119 PAPERS • 14 BENCHMARKS
Virtual KITTI is a photo-realistic synthetic video dataset designed to learn and evaluate computer vision models for several video understanding tasks: object detection and multi-object tracking, scene-level and instance-level semantic segmentation, optical flow, and depth estimation.
119 PAPERS • 1 BENCHMARK
The CityPersons dataset is a subset of Cityscapes which only consists of person annotations. There are 2975 images for training, 500 and 1575 images for validation and testing. The average of the number of pedestrians in an image is 7. The visible-region and full-body annotations are provided.
118 PAPERS • 2 BENCHMARKS
JFT-300M is an internal Google dataset used for training image classification models. Images are labeled using an algorithm that uses complex mixture of raw web signals, connections between web-pages and user feedback. This results in over one billion labels for the 300M images (a single image can have multiple labels). Of the billion image labels, approximately 375M are selected via an algorithm that aims to maximize label precision of selected images.
118 PAPERS • 1 BENCHMARK
The MSRA-TD500 dataset is a text detection dataset that contains 300 training images and 200 test images. Text regions are arbitrarily orientated and annotated at sentence level. Different from the other datasets, it contains both English and Chinese text.
117 PAPERS • 1 BENCHMARK
The Meta-Dataset benchmark is a large few-shot learning benchmark and consists of multiple datasets of different data distributions. It does not restrict few-shot tasks to have fixed ways and shots, thus representing a more realistic scenario. It consists of 10 datasets from diverse domains:
117 PAPERS • 2 BENCHMARKS
The “VehicleID” dataset contains CARS captured during the daytime by multiple real-world surveillance cameras distributed in a small city in China. There are 26,267 vehicles (221,763 images in total) in the entire dataset. Each image is attached with an id label corresponding to its identity in real world. In addition, the dataset contains manually labelled 10319 vehicles (90196 images in total) of their vehicle model information(i.e.“MINI-cooper”, “Audi A6L” and “BWM 1 Series”).
117 PAPERS • 4 BENCHMARKS
Color BSD68 dataset for image denoising benchmarks is part of The Berkeley Segmentation Dataset and Benchmark. It is used for measuring image denoising algorithms performance. It contains 68 images.
116 PAPERS • 16 BENCHMARKS
The Freiburg-Berkeley Motion Segmentation Dataset (FBMS-59) is an extension of the BMS dataset with 33 additional video sequences. A total of 720 frames is annotated. It has pixel-accurate segmentation annotations of moving objects. FBMS-59 comes with a split into a training set and a test set.
116 PAPERS • 3 BENCHMARKS
SUN3D contains a large-scale RGB-D video database, with 8 annotated sequences. Each frame has a semantic segmentation of the objects in the scene and information about the camera pose. It is composed by 415 sequences captured in 254 different spaces, in 41 different buildings. Moreover, some places have been captured multiple times at different moments of the day.
114 PAPERS • NO BENCHMARKS YET
The 20BN-SOMETHING-SOMETHING dataset is a large collection of labeled video clips that show humans performing pre-defined basic actions with everyday objects. The dataset was created by a large number of crowd workers. It allows machine learning models to develop fine-grained understanding of basic actions that occur in the physical world. It contains 108,499 videos, with 86,017 in the training set, 11,522 in the validation set and 10,960 in the test set. There are 174 labels.
114 PAPERS • 3 BENCHMARKS
The MegaDepth dataset is a dataset for single-view depth prediction that includes 196 different locations reconstructed from COLMAP SfM/MVS.
113 PAPERS • NO BENCHMARKS YET
The Adience dataset, published in 2014, contains 26,580 photos across 2,284 subjects with a binary gender label and one label from eight different age groups, partitioned into five splits. The key principle of the data set is to capture the images as close to real world conditions as possible, including all variations in appearance, pose, lighting condition and image quality, to name a few.
112 PAPERS • 6 BENCHMARKS
NABirds V1 is a collection of 48,000 annotated photographs of the 400 species of birds that are commonly observed in North America. More than 100 photographs are available for each species, including separate annotations for males, females and juveniles that comprise 700 visual categories. This dataset is to be used for fine-grained visual categorization experiments.
112 PAPERS • 1 BENCHMARK
Aff-Wild is a dataset for emotion recognition from facial images in a variety of head poses, illumination conditions and occlusions.
111 PAPERS • NO BENCHMARKS YET
The LUNA challenges provide datasets for automatic nodule detection algorithms using the largest publicly available reference database of chest CT scans, the LIDC-IDRI data set. In LUNA16, participants develop their algorithm and upload their predictions on 888 CT scans in one of the two tracks: 1) the complete nodule detection track where a complete CAD system should be developed, or 2) the false positive reduction track where a provided set of nodule candidates should be classified.
111 PAPERS • 2 BENCHMARKS
RESISC45 dataset is a dataset for Remote Sensing Image Scene Classification (RESISC). It contains 31,500 RGB images of size 256×256 divided into 45 scene classes, each class containing 700 images. Among its notable features, RESISC45 contains varying spatial resolution ranging from 20cm to more than 30m/px.
111 PAPERS • 1 BENCHMARK
AFLW2000-3D is a dataset of 2000 images that have been annotated with image-level 68-point 3D facial landmarks. This dataset is used for evaluation of 3D facial landmark detection models. The head poses are very diverse and often hard to be detected by a CNN-based face detector.
110 PAPERS • 8 BENCHMARKS
The Caltech Occluded Faces in the Wild (COFW) dataset is designed to present faces in real-world conditions. Faces show large variations in shape and occlusions due to differences in pose, expression, use of accessories such as sunglasses and hats and interactions with objects (e.g. food, hands, microphones, etc.). All images were hand annotated using the same 29 landmarks as in LFPW. Both the landmark positions as well as their occluded/unoccluded state were annotated. The faces are occluded to different degrees, with large variations in the type of occlusions encountered. COFW has an average occlusion of over 23.
110 PAPERS • 5 BENCHMARKS
OTB2013 is the previous version of the current OTB2015 Visual Tracker Benchmark. It contains only 50 tracking sequences, as opposed to the 100 sequences in the current version of the benchmark.
110 PAPERS • 2 BENCHMARKS
CMU Panoptic is a large scale dataset providing 3D pose annotations (1.5 millions) for multiple people engaging social activities. It contains 65 videos (5.5 hours) with multi-view annotations, but only 17 of them are in multi-person scenario and have the camera parameters.
110 PAPERS • 4 BENCHMARKS
Permuted MNIST is an MNIST variant that consists of 70,000 images of handwritten digits from 0 to 9, where 60,000 images are used for training, and 10,000 images for test. The difference of this dataset from the original MNIST is that each of the ten tasks is the multi-class classification of a different random permutation of the input pixels.
SHAPES is a dataset of synthetic images designed to benchmark systems for understanding of spatial and logical relations among multiple objects. The dataset consists of complex questions about arrangements of colored shapes. The questions are built around compositions of concepts and relations, e.g. Is there a red shape above a circle? or Is a red shape blue?. Questions contain between two and four attributes, object types, or relationships. There are 244 questions and 15,616 images in total, with all questions having a yes and no answer (and corresponding supporting image). This eliminates the risk of learning biases.
110 PAPERS • 1 BENCHMARK
The Chairs dataset contains rendered images of around 1000 different three-dimensional chair models.
109 PAPERS • 1 BENCHMARK
RobustBench is a benchmark of adversarial robustness, which as accurately as possible reflects the robustness of the considered models within a reasonable computational budget. To this end, we start by considering the image classification task and introduce restrictions (possibly loosened in the future) on the allowed models.
109 PAPERS • NO BENCHMARKS YET
The NLPR dataset for salient object detection consists of 1,000 image pairs captured by a standard Microsoft Kinect with a resolution of 640×480. The images include indoor and outdoor scenes (e.g., offices, campuses, streets and supermarkets).
108 PAPERS • 1 BENCHMARK
SCC Data Set
108 PAPERS • 3 BENCHMARKS
CORe50 is a dataset designed for assessing Continual Learning techniques in an Object Recognition context.
107 PAPERS • NO BENCHMARKS YET
Sensory ecologists have found that this s background matching camouflage strategy works by deceiving the visual perceptual system of the observer. Naturally, addressing concealed object detection (COD) requires a significant amount of visual perception knowledge. Understanding COD has not only scientific value in itself, but it also important for applications in many fundamental fields, such as computer vision (e.g., for search-and-rescue work, or rare species discovery), medicine (e.g., polyp segmentation, lung infection segmentation), agriculture (e.g., locust detection to prevent invasion), and art (e.g., recreational art). The high intrinsic similarities between the targets and non-targets make COD far more challenging than traditional object segmentation/detection. Although it has gained increased attention recently, studies on COD still remain scarce, mainly due to the lack of a sufficiently large dataset and a standard benchmark like Pascal-VOC, ImageNet, MS-COCO, ADE20K, and DA
106 PAPERS • 2 BENCHMARKS
The Georgia Tech Egocentric Activities (GTEA) dataset contains seven types of daily activities such as making sandwich, tea, or coffee. Each activity is performed by four different people, thus totally 28 videos. For each video, there are about 20 fine-grained action instances such as take bread, pour ketchup, in approximately one minute.
105 PAPERS • 2 BENCHMARKS
The smallNORB dataset is a datset for 3D object recognition from shape. It contains images of 50 toys belonging to 5 generic categories: four-legged animals, human figures, airplanes, trucks, and cars. The objects were imaged by two cameras under 6 lighting conditions, 9 elevations (30 to 70 degrees every 5 degrees), and 18 azimuths (0 to 340 every 20 degrees). The training set is composed of 5 instances of each category (instances 4, 6, 7, 8 and 9), and the test set of the remaining 5 instances (instances 0, 1, 2, 3, and 5).
105 PAPERS • 1 BENCHMARK
The FER+ dataset is an extension of the original FER dataset, where the images have been re-labelled into one of 8 emotion types: neutral, happiness, surprise, sadness, anger, disgust, fear, and contempt.
104 PAPERS • 2 BENCHMARKS
FreiHAND is a 3D hand pose dataset which records different hand actions performed by 32 people. For each hand image, MANO-based 3D hand pose annotations are provided. It currently contains 32,560 unique training samples and 3960 unique samples for evaluation. The training samples are recorded with a green screen background allowing for background removal. In addition, it applies three different post processing strategies to training samples for data augmentation. However, these post processing strategies are not applied to evaluation samples.
103 PAPERS • 1 BENCHMARK