Fine-Grained Image Classification
Fine-Grained Image Classification is a task in computer vision where the goal is to classify images into subcategories within a larger category. For example, classifying different species of birds or different types of flowers. This task is considered to be fine-grained because it requires the model to distinguish between subtle differences in visual appearance and patterns, making it more challenging than regular image classification tasks.
( Image credit: Looking for the Devil in the Details )
Papers
Showing 1–10 of 353 papers
All datasetsStanford CarsFGVC-AircraftCUB-200-2011NABirdsOxford 102 FlowersStanford DogsOxford-IIIT PetsCaltech-101Food-101Oxford-IIIT Pet DatasetCompCarsBird-225
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MP | Accuracy | 97.3 | — | Unverified |
| 2 | MPSA | Accuracy | 95.4 | — | Unverified |
| 3 | ViT-NeT (DeiT-III-B) | Accuracy | 93.6 | — | Unverified |
| 4 | µ2Net+ (ViT-L/16) | Accuracy | 93.5 | — | Unverified |
| 5 | SIM-OFE | Accuracy | 93.3 | — | Unverified |
| 6 | WS_DAN-SAC | Accuracy | 93.1 | — | Unverified |
| 7 | SEB+EfficientNet-B5 | Accuracy | 93 | — | Unverified |
| 8 | TPSKG | Accuracy | 92.5 | — | Unverified |
| 9 | RAMS-Trans | Accuracy | 92.4 | — | Unverified |
| 10 | SFETrans | Accuracy | 92.4 | — | Unverified |