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.
Papers
Showing 1–10 of 10419 papers
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | efficient adaptive ensembling | Accuracy | 99.61 | — | Unverified |
| 2 | ViT-H/14 | Percentage correct | 99.5 | — | Unverified |
| 3 | DINOv2 (ViT-g/14, frozen model, linear eval) | Percentage correct | 99.5 | — | Unverified |
| 4 | µ2Net (ViT-L/16) | Percentage correct | 99.49 | — | Unverified |
| 5 | ViT-L/16 | Percentage correct | 99.42 | — | Unverified |
| 6 | CaiT-M-36 U 224 | Percentage correct | 99.4 | — | Unverified |
| 7 | CvT-W24 | Percentage correct | 99.39 | — | Unverified |
| 8 | BiT-L (ResNet) | Percentage correct | 99.37 | — | Unverified |
| 9 | RDNet-L (224 res, IN-1K pretrained) | Percentage correct | 99.31 | — | Unverified |
| 10 | RDNet-B (224 res, IN-1K pretrained) | Percentage correct | 99.31 | — | Unverified |