Domain Adaptation

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. Source: http://yann.lecun.com/exdb/mnist/ Image Source: https://en.wikipedia.org/wiki/MNIST_database#/media/File:MnistExamples.png

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. Source: A Review on Deep Learning Techniques Applied to Semantic Segmentation Image Source: https://www.cityscapes-dataset.com/dataset-overview/

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. Source: Reading Digits in Natural Images with Unsupervised Feature Learning Image Source: http://ufldl.stanford.edu/housenumbers/

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. Source: Generative Probabilistic Novelty Detection with Adversarial Autoencoders Image Source: https://github.com/zalandoresearch/fashion-mnist

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. Source: Multi-component Image Translation for Deep Domain Generalization Image Source: Wen et al

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. Source: A Survey of Pruning Methods for Efficient Person Re-identification Across Domains Image Source: https://www.researchgate.net/publication/306358716_A_Discriminative_Null_Space_based_Deep_Learning_Approach_for_Person_Re-Identification

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!”. Source: What is being transferred in transfer learning? Image Source: http://ai.bu.edu/M3SDA/

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. Source: Deep Domain-Adversarial Image Generation for Domain Generalisation Image Source: https://www.researchgate.net/figure/Sample-images-from-PACS-dataset-Each-row-represents-a-domain-and-each-column-represents_fig1_334695033

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. Source: Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors Image Source: https://www.researchgate.net/publication/310953258

ImageNet-C is an open source data set that consists of algorithmically generated corruptions (blur, noise) applied to the ImageNet test-set. Source: Selective Brain Damage: Measuring the Disparate Impact of Model Pruning Image Source: https://arxiv.org/pdf/1807.01697.pdf

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/

Common corruptions dataset for CIFAR10

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

Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving. Researchers are usually constrained to study a small set of problems on one dataset, while real-world computer vision applications require performing tasks of various complexities. We construct BDD100K, the largest driving video dataset with 100K videos and 10 tasks to evaluate the exciting progress of image recognition algorithms on autonomous driving. The dataset possesses geographic, environmental, and weather diversity, which is useful for training models that are less likely to be surprised by new conditions. Based on this diverse dataset, we build a benchmark for heterogeneous multitask learning and study how to solve the tasks together. Our experiments show that special training strategies are needed for existing models to perform such heterogeneous tasks. BDD100K opens the door for future studies in this important venue. More detail is at the dataset home page.

USPS is a digit dataset automatically scanned from envelopes by the U.S. Postal Service containing a total of 9,298 16×16 pixel grayscale samples; the images are centered, normalized and show a broad range of font styles. Source: Hallucinating Agnostic Images to Generalize Across Domains Image Source: https://ieeexplore.ieee.org/document/291440

The ImageNet-A dataset consists of real-world, unmodified, and naturally occurring examples that are misclassified by ResNet models. Source: On Robustness and Transferability of Convolutional Neural Networks Image Source: https://github.com/hendrycks/natural-adv-examples

The Replica Dataset is a dataset of high quality reconstructions of a variety of indoor spaces. Each reconstruction has clean dense geometry, high resolution and high dynamic range textures, glass and mirror surface information, planar segmentation as well as semantic class and instance segmentation. Source: The Replica Dataset: A Digital Replica of Indoor Spaces

The GTA5 dataset contains 24966 synthetic images with pixel level semantic annotation. The images have been rendered using the open-world video game Grand Theft Auto 5 and are all from the car perspective in the streets of American-style virtual cities. There are 19 semantic classes which are compatible with the ones of Cityscapes dataset. Source: Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation Image Source: Richter et al

The German Traffic Sign Recognition Benchmark (GTSRB) contains 43 classes of traffic signs, split into 39,209 training images and 12,630 test images. The images have varying light conditions and rich backgrounds. Source: Invisible Backdoor Attacks Against Deep Neural Networks Image Source: https://www.researchgate.net/figure/An-example-of-the-43-traffic-sign-classes-of-GTSRB-dataset_fig9_311896388

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

Foggy Cityscapes is a synthetic foggy dataset which simulates fog on real scenes. Each foggy image is rendered with a clear image and depth map from Cityscapes. Thus the annotations and data split in Foggy Cityscapes are inherited from Cityscapes. Source: Exploring Object Relation in Mean Teacher for Cross-Domain Detection Image Source: http://people.ee.ethz.ch/~csakarid/SFSU_synthetic/

VisDA-2017 is a simulation-to-real dataset for domain adaptation with over 280,000 images across 12 categories in the training, validation and testing domains. The training images are generated from the same object under different circumstances, while the validation images are collected from MSCOCO.. Source: Gradually Vanishing Bridge for Adversarial Domain Adaptation Image Source: http://ai.bu.edu/visda-2017/

OpenSubtitles is collection of multilingual parallel corpora. The dataset is compiled from a large database of movie and TV subtitles and includes a total of 1689 bitexts spanning 2.6 billion sentences across 60 languages.

MNIST-M is created by combining MNIST digits with the patches randomly extracted from color photos of BSDS500 as their background. It contains 59,001 training and 90,001 test images. Source: A Review of Single-Source Deep Unsupervised Visual Domain Adaptation Image Source: https://arxiv.org/pdf/1505.07818v4.pdf

This paper introduces the pipeline to scale the largest dataset in egocentric vision EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version (EPIC-KITCHENS-55), EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection also enables evaluating the "test of time" - i.e. whether models trained on data collected in 2018 can generalise to new footage collected under the same hypotheses albeit "two years on". The dataset is aligned with 6 challenges: action recognition (full and weak supervision), action detection, action anticipation, cross-modal retrieval (from captions), as well as unsupervised domain adaptation for action recognition. For each challenge, we define the task, provide baselines and evaluation metrics.

Freesound Dataset 50k (or FSD50K for short) is an open dataset of human-labeled sound events containing 51,197 Freesound clips unequally distributed in 200 classes drawn from the AudioSet Ontology. FSD50K has been created at the Music Technology Group of Universitat Pompeu Fabra. It consists mainly of sound events produced by physical sound sources and production mechanisms, including human sounds, sounds of things, animals, natural sounds, musical instruments and more. Source: https://zenodo.org/record/4060432 Image Source: https://labs.freesound.org/datasets/

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”). Source: https://www.pkuml.org/resources/pku-vehicleid.html Image Source: https://www.pkuml.org/resources/pku-vehicleid.html

The 'shape bias' dataset was introduced in Geirhos et al. (ICLR 2019) and consists of 224x224 images with conflicting texture and shape information (e.g., cat shape with elephant texture). This is used to measure the shape vs. texture bias of image classifiers.

Rationale and objectives: Computer-aided detection and diagnosis (CAD) systems have been developed in the past two decades to assist radiologists in the detection and diagnosis of lesions seen on breast imaging exams, thus providing a second opinion. Mammographic databases play an important role in the development of algorithms aiming at the detection and diagnosis of mammary lesions. However, available databases often do not take into consideration all the requirements needed for research and study purposes. This article aims to present and detail a new mammographic database. Materials and methods: Images were acquired at a breast center located in a university hospital (Centro Hospitalar de S. João [CHSJ], Breast Centre, Porto) with the permission of the Portuguese National Committee of Data Protection and Hospital's Ethics Committee. MammoNovation Siemens full-field digital mammography, with a solid-state detector of amorphous selenium was used. **Results: **The new database-INbreast-has a total of 115 cases (410 images) from which 90 cases are from women with both breasts affected (four images per case) and 25 cases are from mastectomy patients (two images per case). Several types of lesions (masses, calcifications, asymmetries, and distortions) were included. Accurate contours made by specialists are also provided in XML format. Conclusion: The strengths of the actually presented database-INbreast-relies on the fact that it was built with full-field digital mammograms (in opposition to digitized mammograms), it presents a wide variability of cases, and is made publicly available together with precise annotations. We believe that this database can be a reference for future works centered or related to breast cancer imaging.

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

IDD is a dataset for road scene understanding in unstructured environments used for semantic segmentation and object detection for autonomous driving. It consists of 10,004 images, finely annotated with 34 classes collected from 182 drive sequences on Indian roads. Source: IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments Image Source: Varma et al

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

The VGG Face dataset is face identity recognition dataset that consists of 2,622 identities. It contains over 2.6 million images. Source: https://www.robots.ox.ac.uk/~vgg/data/vgg_face/ Image Source: http://www.bmva.org/bmvc/2015/papers/paper041/paper041.pdf

SIM10k is a synthetic dataset containing 10,000 images, which is rendered from the video game Grand Theft Auto V (GTA5). Source: Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation Image Source: https://arxiv.org/pdf/1610.01983.pdf

ASPEC, Asian Scientific Paper Excerpt Corpus, is constructed by the Japan Science and Technology Agency (JST) in collaboration with the National Institute of Information and Communications Technology (NICT). It consists of a Japanese-English paper abstract corpus of 3M parallel sentences (ASPEC-JE) and a Japanese-Chinese paper excerpt corpus of 680K parallel sentences (ASPEC-JC). This corpus is one of the achievements of the Japanese-Chinese machine translation project which was run in Japan from 2006 to 2010. Source: ASPEC Image Source: https://www.aclweb.org/anthology/L16-1350.pdf

1. 5987 high spatial resolution (0.3 m) remote sensing images from Nanjing, Changzhou, and Wuhan 2. Focus on different geographical environments between Urban and Rural 3. Advance both semantic segmentation and domain adaptation tasks 4. Three considerable challenges: * Multi-scale objects * Complex background samples * Inconsistent class distributions Two contests are held on the Codalab: <b>LoveDA Semantic Segmentation Challenge</b>, <b>LoveDA Unsupervised Domain Adaptation Challenge</b>