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 | 96.81 | — | Unverified |
| 2 | EffNet-L2 (SAM) | Percentage correct | 96.08 | — | Unverified |
| 3 | Swin-L + ML-Decoder | Percentage correct | 95.1 | — | Unverified |
| 4 | µ2Net (ViT-L/16) | Percentage correct | 94.95 | — | Unverified |
| 5 | ViT-B-16 (ImageNet-21K-P pretrain) | Percentage correct | 94.2 | — | Unverified |
| 6 | CvT-W24 | Percentage correct | 94.09 | — | Unverified |
| 7 | ViT-B/16 (PUGD) | Percentage correct | 93.95 | — | Unverified |
| 8 | Heinsen Routing + BEiT-large 16 224 | Percentage correct | 93.8 | — | Unverified |
| 9 | BiT-L (ResNet) | Percentage correct | 93.51 | — | Unverified |
| 10 | VIT-L/16 (Spinal FC, Background) | Percentage correct | 93.31 | — | Unverified |