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
505개FC100 5-way (1-shot)FC100 5-way (5-shot)ImageNet-1K (with DeiT-T)Meta-DatasetOmniBenchmarkiNaturalist 2019CIFAR-10, 40 LabelsCIFAR-100, 400 LabelsOMNIGLOT - 1-Shot, 20-wayRESISC45ANIMALDF20DF20 - MiniEMNIST-BalancedImageNet-1K (With LV-ViT-S)OMNIGLOT - 5-Shot, 20-wayOxford-IIIT PetsiNaturalistCaltech-101ColonINST-v1 (Seen)ColonINST-v1 (Unseen)OMNIGLOT - 1-Shot, 5-waySVHN, 1000 labelsCIFAR-100, 2500 LabelsMini-ImageNet - 1-Shot LearningOMNIGLOT - 5-Shot, 5-wayWebVision-1000EuroSATFood-101MIMIC-CXR-LT