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 | EffNet-L2 (SAM) | Accuracy | 97.1 | — | Unverified |
| 2 | BiT-L (ResNet) | Accuracy | 96.62 | — | Unverified |
| 3 | µ2Net+ (ViT-L/16) | Accuracy | 95.5 | — | Unverified |
| 4 | µ2Net (ViT-L/16) | Accuracy | 95.3 | — | Unverified |
| 5 | BiT-M (ResNet) | Accuracy | 94.47 | — | Unverified |
| 6 | Assemble-ResNet-FGVC-50 | Accuracy | 94.3 | — | Unverified |
| 7 | NAT-M4 | Accuracy | 94.3 | — | Unverified |
| 8 | NAT-M3 | Accuracy | 94.1 | — | Unverified |
| 9 | NAT-M2 | Accuracy | 93.5 | — | Unverified |
| 10 | ResNet-152-SAM | Accuracy | 93.3 | — | Unverified |