Papers with Code · CC BY-SA 4.0
Image Classification
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.
<span class="description-source">Source: Metamorphic Testing for Object Detection Systems </span>
데이터셋
505개CIFAR-FS 5-way (1-shot)CUB 200 5-way 1-shotFashion-MNISTIndian PinesVTAB-1kImageNet V2Pavia UniversityCUB 200 5-way 5-shotCIFAR-100-LT (ρ=10)RVL-CDIPNABirdsSequential MNISTPlaces-LTcifar-100, 10000 LabelsCIFAR-10-LT (ρ=100)Mini-Imagenet 5-way (1-shot)Mini-Imagenet 5-way (5-shot)CIFAR-10, 250 LabelsCIFAR-10N-AggregateKuzushiji-MNISTCIFAR-100-LT (ρ=50)CIFAR-10N-WorstOxford 102 FlowersCIFAR-100NCIFAR-10N-Random1Stanford CarsStanford DogsCIFAR-10N-Random2CIFAR-10N-Random3Tiny ImageNet Classification