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 | Pre trained wide-resnet-101 | Accuracy | 97.76 | — | Unverified |
| 2 | Bamboo (ViT-B/16) | Accuracy | 94.8 | — | Unverified |
| 3 | UL-Hopfield (ULH) | Accuracy | 91 | — | Unverified |
| 4 | ResNet-101 (ideal number of groups) | Top-1 Error Rate | 22.25 | — | Unverified |
| 5 | SE-ResNet-101 (SAP) | Top-1 Error Rate | 15.95 | — | Unverified |
| 6 | PreResNet-101 | Top-1 Error Rate | 15.8 | — | Unverified |
| 7 | AutoAugment | Top-1 Error Rate | 13.07 | — | Unverified |
| 8 | ViT-S/16 (RPE w/ GAB) | Top-1 Error Rate | 9.8 | — | Unverified |
| 9 | SEER (RegNet10B - linear eval) | Top-1 Error Rate | 9 | — | Unverified |
| 10 | NNCLR | Top-1 Error Rate | 8.7 | — | Unverified |