Papers with Code 아카이브

Image Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
33
평가표
177
보존된 평가 기록
2,906

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

WebFG-496

WebFG-496 is a dataset for fine-grained recognition that contains 200 subcategories of the "Bird" (Web-bird), 100 subcategories of the Aircraft" (Web-aircraft), and 196 subcategories of the "Car" (Web-car). It has a total number of 53339 web training images.

Colored-MNIST(with spurious correlation)

This is a dataset with spurious correlations which can be used to evaluate machine learning methods for out-of-distribution generalization, causal inference, and related field.

F-CelebA (10 tasks)

F-CelebA - This dataset is adapted from federated learning. Federated learning is an emerging machine learning paradigm with an emphasis on data privacy. The idea is to train through model aggregation rather than conventional data aggregation and keep local data staying on the local device. This dataset naturally consists of similar tasks and each of the 10 tasks contains images of a celebrity labeled by whether he/she is smiling or not. More detailed please check page https://github.com/ZixuanKe/CAT

Food-101N

The Food-101N dataset is introduced in "CleanNet: Transfer Learning for Scalable Image Training with Label Noise (CVPR'18). It is an image dataset containing about 310,009 images of food recipes classified in 101 classes (categories). Food-101N and the Food-101 dataset share the same 101 classes, whereas Food-101N has much more images and is more noisy. Food-101N is designed for the following two tasks: 1)Learning image classification with label noise 2)Label noise detection

Galaxy Zoo DECaLS

Approx. 300,000 images of galaxies labelled by shape. Labels are from www.galaxyzoo.org volunteers, and are noisy. Images are from the DECaLS telescope survey. Also includes predictions from an ensemble of EfficientNets, each using MC Dropout and a novel probabilistic loss function.

GBCU

GBCU is the first public dataset for Gallbladder Cancer identification from Ultrasound images. GBCU contains a total of 1255 (432 normal, 558 benign, and 265 malignant) annotated abdominal Ultrasound images collected from 218 patients. Of the 218 patients, 71, 100, and 47 were from the normal, benign, and malignant classes, respectively. The sizes of the training and testing sets are 1133 and 122, respectively. To ensure generalization to unseen patients, all images of any particular patient were either in the train or the test split. We acquired data samples from patients referred to PGIMER, Chandigarh (a referral hospital in Northern India) for abdominal ultrasound examinations of suspected Gallbladder pathologies. The study was approved by the Ethics Committee of PGIMER, Chandigarh. We obtained informed written consent from the patients at the time of recruitment, and protect their privacy by fully anonymizing the data. Grayscale B-mode static images, including both sagittal and axial sections, were recorded by radiologists for each patient using a Logiq S8 machine. Each image is labeled as one of the three classes - normal, benign, or malignant. The ground-truth labels were biopsy-proven to assert the correctness. Additionally, bounding-box annotations for abnormal pathologies (e.g. stone, benign mural thickening, or malignancy), and the GB are provided. The GBCU dataset is suitable for both image classification and object detection tasks. Apart from the Gallbladder Cancer, the dataset can also be used for detection of several other pathologies.

Im2GPS

Dataset of over 6 million GPS-tagged images from Flickr. Training dataset is private. Test dataset is composed by 237 images.

Malaria Dataset

The dataset contains a total of 27,558 cell images with equal instances of parasitized and uninfected cells. Source: Malaria Dataset

Moviescope

Moviescope is a large-scale dataset of 5,000 movies with corresponding video trailers, posters, plots and metadata. Moviescope is based on the IMDB 5000 dataset consisting of 5.043 movie records. It is augmented by crawling video trailers associated with each movie from YouTube and text plots from Wikipedia. Source: Moviescope: Large-scale Analysis of Movies using Multiple Modalities

OOD-CV

Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One reason is that existing robustness benchmarks are limited, as they either rely on synthetic data or ignore the effects of individual nuisance factors. We introduce OOD-CV, a benchmark dataset that includes out-of-distribution examples of 10 object categories in terms of pose, shape, texture, context and the weather conditions, and enables benchmarking models for image classification, object detection, and 3D pose estimation. In addition to this novel dataset, we contribute extensive experiments using popular baseline methods, which reveal that: 1. Some nuisance factors have a much stronger negative effect on the performance compared to others, also depending on the vision task. 2. Current approaches to enhance robustness have only marginal effects, and can even reduce robustness. 3. We do not observe significant differences between convolutional and transformer architectures. We believe our dataset provides a rich test bed to study robustness and will help push forward research in this area.

Open Images V7

Open Images is a computer vision dataset covering ~9 million images with labels spanning thousands of object categories. A subset of 1.9M includes diverse annotations types. - 15,851,536 boxes on 600 classes - 2,785,498 instance segmentations on 350 classes - 3,284,280 relationship annotations on 1,466 relationships - 675,155 localized narratives (synchronized voice, mouse trace, and text caption) - 66,391,027 point-level annotations on 5,827 classes - 61,404,966 image-level labels on 20,638 classes Images are under a CC BY 2.0 license, annotations under CC BY 4.0 license.

ImageNet-Hard

ImageNet-Hard is a new benchmark that comprises 10,980 images collected from various existing ImageNet-scale benchmarks (ImageNet, ImageNet-V2, ImageNet-Sketch, ImageNet-C, ImageNet-R, ImageNet-ReaL, ImageNet-A, and ObjectNet). This dataset poses a significant challenge to state-of-the-art vision models as merely zooming in often fails to improve their ability to classify images correctly. As a result, even the most advanced models, such as CLIP-ViT-L/14@336px, struggle to perform well on this dataset, achieving a mere 2.02% accuracy.

ImageNet-Patch

ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches Adversarial patches are optimized contiguous pixel blocks in an input image that cause a machine-learning model to misclassify it. However, their optimization is computationally demanding, and requires careful hyperparameter tuning, potentially leading to suboptimal robustness evaluations. To overcome these issues, we propose ImageNet-Patch, a dataset to benchmark machine-learning models against adversarial patches. It consists of a set of patches, optimized to generalize across different models, and readily applicable to ImageNet data after preprocessing them with affine transformations. This process enables an approximate yet faster robustness evaluation, leveraging the transferability of adversarial perturbations.

InsPLAD

InsPLAD is a Dataset for Power Line Asset Inspection containing 10,607 high-resolution Unmanned Aerial Vehicles colour images. It contains 17 unique power line assets captured from real-world operating power lines. Some of those assets (five, to be precise) are also annotated regarding their conditions. They present the following defects: corrosion (4 of them), broken/missing cap (1 of them), and bird's nest presence (1 of them). Three image-level computer vision tasks covered by InsPLAD: * Object detection, evaluated through the AP metric * Defect classification, evaluated through Balanced Accuracy * Anomaly detection, evaluated through the AUROC metric

Intel Image Classification

Context This is image data of Natural Scenes around the world. Content This Data contains around 25k images of size 150x150 distributed under 6 categories. {'buildings' -> 0, 'forest' -> 1, 'glacier' -> 2, 'mountain' -> 3, 'sea' -> 4, 'street' -> 5 } The Train, Test and Prediction data is separated in each zip files. There are around 14k images in Train, 3k in Test and 7k in Prediction. This data was initially published on https://datahack.analyticsvidhya.com by Intel to host a Image classification Challenge. Acknowledgements Thanks to https://datahack.analyticsvidhya.com for the challenge and Intel for the Data Photo by Jan Böttinger on Unsplash Inspiration Want to build powerful Neural network that can classify these images with more accuracy.

MuMiN

MuMiN is a misinformation graph dataset containing rich social media data (tweets, replies, users, images, articles, hashtags), spanning 21 million tweets belonging to 26 thousand Twitter threads, each of which have been semantically linked to 13 thousand fact-checked claims across dozens of topics, events and domains, in 41 different languages, spanning more than a decade. MuMiN fills a gap in the existing misinformation datasets in multiple ways: - By having a large amount of social media information which have been semantically linked to fact-checked claims on an individual basis. - By featuring 41 languages, enabling evaluation of multilingual misinformation detection models. - By featuring both tweets, articles, images, social connections and hashtags, enabling multimodal approaches to misinformation detection. MuMiN features two node classification tasks, related to the veracity of a claim: - Claim classification: Determine the veracity of a claim, given its social network context. - Tweet classification: Determine the likelihood that a social media post to be fact-checked is discussing a misleading claim, given its social network context. To use the dataset, see the "Getting Started" guide and tutorial at the MuMiN website.

NIH-CXR-LT

NIH-CXR-LT. NIH ChestXRay14 contains over 100,000 chest X-rays labeled with 14 pathologies, plus a “No Findings” class. We construct a single-label, long-tailed version of the NIH ChestXRay14 dataset by introducing five new disease findings described above. The resulting NIH-CXR-LT dataset has 20 classes, including 7 head classes, 10 medium classes, and 3 tail classes. NIH-CXR-LT contains 88,637 images labeled with one of 19 thorax diseases, with 68,058 training and 20,279 test images. The validation and balanced test sets contain 15 and 30 images per class, respectively.

RF100

The evaluation of object detection models is usually performed by optimizing a single metric, e.g. mAP, on a fixed set of datasets, e.g. Microsoft COCO and Pascal VOC. Due to image retrieval and annotation costs, these datasets consist largely of images found on the web and do not represent many real-life domains that are being modelled in practice, e.g. satellite, microscopic and gaming, making it difficult to assert the degree of generalization learned by the model. We introduce the Roboflow-100 (RF100) consisting of 100 datasets, 7 imagery domains, 224,714 images, and 805 class labels with over 11,170 labelling hours. We derived RF100 from over 90,000 public datasets, 60 million public images that are actively being assembled and labelled by computer vision practitioners in the open on the web application Roboflow Universe. By releasing RF100, we aim to provide a semantically diverse, multi-domain benchmark of datasets to help researchers test their model's generalizability with real-life data. RF100 download and benchmark replication are available on GitHub.

Sewer-ML

Sewer-ML is a sewer defect dataset. It contains 1.3 million images, from 75,618 videos collected from three Danish water utility companies over nine years. All videos have been annotated by licensed sewer inspectors following the Danish sewer inspection standard, Fotomanualen. This leads to consistent and reliable annotations, and a total of 17 annotated defect classes. Source: Sewer-ML Image Source: Sewer-ML

SIPaKMeD

  • a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

Sports10

  • Games dataset containing 100,000 Gameplay Images of 175 Video Games across 10 Sports Genres - AMERICAN FOOTBALL, BASKETBALL, BIKE RACING, CAR RACING, FIGHTING, HOCKEY, SOCCER, TABLE TENNIS, TENNIS. - Hand-curated images to remove menu/transition frames and only include gameplay sequences. - Games are divided into three visual styling categories: RETRO (arcade-style, 1990s and earlier) MODERN (roughly 2000s) PHOTOREAL (roughly late 2010s).

Tencent ML-Images

Tencent ML-Images is a large open-source multi-label image database, including 17,609,752 training and 88,739 validation image URLs, which are annotated with up to 11,166 categories. Source: Tencent ML-Images

Tobacco-3482

The Tobacco-3482 dataset consists of document images belonging to 10 classes such as letter, form, email, resume, memo, etc. The dataset has 3482 images.

BIOSCAN-5M

As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, we present the BIOSCAN-5M Insect dataset to the machine learning community. BIOSCAN-5M is a comprehensive dataset containing multi-modal information for over 5 million insect specimens, and it significantly expands existing image-based biological datasets by including taxonomic labels, raw nucleotide barcode sequences, assigned barcode index numbers, geographical information, and specimen size. Every record has both image and DNA data. Each record of the BIOSCAN-5M dataset contains six primary attributes: RGB image DNA barcode sequence Barcode Index Number (BIN) Biological taxonomic classification Geographical information Specimen size

Botswana

Botswana is a hyperspectral image classification dataset. The NASA EO-1 satellite acquired a sequence of data over the Okavango Delta, Botswana in 2001-2004. The Hyperion sensor on EO-1 acquires data at 30 m pixel resolution over a 7.7 km strip in 242 bands covering the 400-2500 nm portion of the spectrum in 10 nm windows. Preprocessing of the data was performed by the UT Center for Space Research to mitigate the effects of bad detectors, inter-detector miscalibration, and intermittent anomalies. Uncalibrated and noisy bands that cover water absorption features were removed, and the remaining 145 bands were included as candidate features: [10-55, 82-97, 102-119, 134-164, 187-220]. The data analyzed in this study, acquired May 31, 2001, consist of observations from 14 identified classes representing the land cover types in seasonal swamps, occasional swamps, and drier woodlands located in the distal portion of the Delta. Source: M Graña, MA Veganzons, B Ayerdi

CI-MNIST

CI-MNIST (Correlated and Imbalanced MNIST) is a variant of MNIST dataset with introduced different types of correlations between attributes, dataset features, and an artificial eligibility criterion. For an input image $x$, the label $y \in \\{1, 0\\}$ indicates eligibility or ineligibility, respectively, given that $x$ is even or odd. The dataset defines the background colors as the protected or sensitive attribute $s \in \\{0, 1\\}$, where blue denotes the unprivileged group and red denotes the privileged group. The dataset was designed in order to evaluate bias-mitigation approaches in challenging setups and be capable of controlling different dataset configurations.

DiagSet

DiagSet is a histopathological dataset for prostate cancer detection. The proposed dataset consists of over 2.6 million tissue patches extracted from 430 fully annotated scans, 4675 scans with assigned binary diagnosis, and 46 scans with diagnosis given independently by a group of histopathologists.

ETHEC

It includes 47,978 butterfly images with a 4-level label-hierarchy. Hierarchy of labels from the ETHEC dataset across 4 levels: family, sub-family, genus and species. 6 family -> 21 sub-family -> 135 genus -> 561 species

EuroSAT-SAR

A SAR version of the EuroSAT dataset. The images were collected from Sentinel-1 GRD products (two bands VV and VH) based on the geocoordinates of the EuroSAT images.

FewSOL

The Few-Shot Object Learning (FewSOL) dataset can be used for object recognition with a few images per object. It contains 336 real-world objects with 9 RGB-D images per object from different views. Object segmentation masks, object poses and object attributes are provided. In addition, synthetic images generated using 330 3D object models are used to augment the dataset. FewSOL dataset can be used to study a set of few-shot object recognition problems such as classification, detection and segmentation, shape reconstruction, pose estimation, keypoint correspondences and attribute recognition. Motivation: If robots can recognize objects from a few exemplar images, it is possible to scale up the number of objects a robot can recognize because collecting a few images per object is a much easier process compared to building a 3D model of an object. In addition, models trained in the meta-learning setting can generalize to new objects without re-training.

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.