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 | Top-1 Accuracy | 82.7 | — | Unverified |
| 2 | LiT | Top-1 Accuracy | 82.5 | — | Unverified |
| 3 | BASIC | Top-1 Accuracy | 82.3 | — | Unverified |
| 4 | ViT-H/14 | Top-5 Accuracy | 82.1 | — | Unverified |
| 5 | EVA-02-CLIP-E/14+ | Top-1 Accuracy | 79.6 | — | Unverified |
| 6 | Baseline (ViT-G/14) | Top-1 Accuracy | 79.03 | — | Unverified |
| 7 | Model soups (ViT-G/14) | Top-1 Accuracy | 78.52 | — | Unverified |
| 8 | MAWS (ViT-6.5B) | Top-1 Accuracy | 77.9 | — | Unverified |
| 9 | MAWS (ViT-2B) | Top-1 Accuracy | 75.8 | — | Unverified |
| 10 | MAWS (ViT-H) | Top-1 Accuracy | 72.6 | — | Unverified |