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 | OmniVec2 | Accuracy | 99.6 | — | Unverified |
| 2 | OmniVec | Accuracy | 99.2 | — | Unverified |
| 3 | DINOv2 (ViT-g/14, frozen model, linear eval) | Accuracy | 96.7 | — | Unverified |
| 4 | ViT R26 + S/32 ( Augmented) | Accuracy | 96.28 | — | Unverified |
| 5 | ALIGN | Accuracy | 96.19 | — | Unverified |
| 6 | EfficientNet-B7 | Accuracy | 95.4 | — | Unverified |
| 7 | IELT | Accuracy | 95.28 | — | Unverified |
| 8 | Bamboo (ViT-B/16) | Accuracy | 95.1 | — | Unverified |
| 9 | TNT-B | Accuracy | 95 | — | Unverified |
| 10 | AutoFormer-S | 384 | Accuracy | 94.9 | — | Unverified |