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 | LRA-diffusion (CLIP ViT) | Top-1 Accuracy | 84.16 | — | Unverified |
| 2 | Robust LR | Top-1 Accuracy | 81.84 | — | Unverified |
| 3 | PGDF (Inception-ResNet-v2) | Top-1 Accuracy | 81.47 | — | Unverified |
| 4 | SSR | Top-1 Accuracy | 80.92 | — | Unverified |
| 5 | CoDiM-Sup (Inception-ResNet-v2) | Top-1 Accuracy | 80.88 | — | Unverified |
| 6 | BtR | Top-1 Accuracy | 80.88 | — | Unverified |
| 7 | RTE (Inception-ResNet-v2) | ImageNet Top-1 Accuracy | 80.84 | — | Unverified |
| 8 | NCR+Mixup+DA (ResNet-50) | Top-1 Accuracy | 80.5 | — | Unverified |
| 9 | CMW-Net-SL+C2D | Top-1 Accuracy | 80.44 | — | Unverified |
| 10 | CoDiM-Self (Inception-ResNet-v2) | Top-1 Accuracy | 80.12 | — | Unverified |