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 | CCT-14/7x2 | Accuracy | 99.76 | — | Unverified |
| 2 | VIT-L/16 (Background) | Accuracy | 99.75 | — | Unverified |
| 3 | CvT-W24 | Accuracy | 99.72 | — | Unverified |
| 4 | Bamboo (ViT-B/16) | Accuracy | 99.7 | — | Unverified |
| 5 | Accuracy | 99.68 | — | Unverified | |
| 6 | ALIGN | Accuracy | 99.65 | — | Unverified |
| 7 | EffNet-L2 (SAM) | Accuracy | 99.65 | — | Unverified |
| 8 | BiT-L (ResNet) | Accuracy | 99.63 | — | Unverified |
| 9 | ConvMLP-S | Accuracy | 99.5 | — | Unverified |
| 10 | ConvMLP-L | Accuracy | 99.5 | — | Unverified |