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 | CoCa (finetuned) | Top 1 Accuracy | 91 | — | Unverified |
| 2 | Model soups (BASIC-L) | Top 1 Accuracy | 90.98 | — | Unverified |
| 3 | Model soups (ViT-G/14) | Top 1 Accuracy | 90.94 | — | Unverified |
| 4 | DaViT-G | Top 1 Accuracy | 90.4 | — | Unverified |
| 5 | Meta Pseudo Labels (EfficientNet-L2) | Top 1 Accuracy | 90.2 | — | Unverified |
| 6 | DaViT-H | Top 1 Accuracy | 90.2 | — | Unverified |
| 7 | SwinV2-G | Top 1 Accuracy | 90.17 | — | Unverified |
| 8 | MAWS (ViT-6.5B) | Top 1 Accuracy | 90.1 | — | Unverified |
| 9 | Florence-CoSwin-H | Top 1 Accuracy | 90.05 | — | Unverified |
| 10 | RevCol-H | Top 1 Accuracy | 90 | — | Unverified |