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 51–75 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 | TResnet-L + PMD | Accuracy | 97.3 | — | Unverified |
| 2 | CMAL-Net | Accuracy | 97.1 | — | Unverified |
| 3 | I2-HOFI | Accuracy | 96.92 | — | Unverified |
| 4 | TResNet-L + ML-Decoder | Accuracy | 96.41 | — | Unverified |
| 5 | DAT | Accuracy | 96.2 | — | Unverified |
| 6 | ALIGN | Accuracy | 96.13 | — | Unverified |
| 7 | SR-GNN | Accuracy | 96.1 | — | Unverified |
| 8 | EffNet-L2 (SAM) | Accuracy | 95.96 | — | Unverified |
| 9 | SaSPA + CAL | Accuracy | 95.72 | — | Unverified |
| 10 | CAP | Accuracy | 95.7 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | I2-HOFI | Accuracy | 96.42 | — | Unverified |
| 2 | SR-GNN | Accuracy | 95.4 | — | Unverified |
| 3 | Inceptionv4 | Accuracy | 95.11 | — | Unverified |
| 4 | CAP | Accuracy | 94.9 | — | Unverified |
| 5 | CSQA-Net | Accuracy | 94.7 | — | Unverified |
| 6 | CMAL-Net | Accuracy | 94.7 | — | Unverified |
| 7 | TBMSL-Net | Accuracy | 94.7 | — | Unverified |
| 8 | PART | Accuracy | 94.6 | — | Unverified |
| 9 | SaSPA + CAL | Accuracy | 94.5 | — | Unverified |
| 10 | AENet | Accuracy | 94.5 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | HERBS | Accuracy | 93.1 | — | Unverified |
| 2 | PIM | Accuracy | 92.8 | — | Unverified |
| 3 | MDCM | Accuracy | 92.5 | — | Unverified |
| 4 | IELT | Accuracy | 91.8 | — | Unverified |
| 5 | CAP | Accuracy | 91.8 | — | Unverified |
| 6 | SFETrans | Accuracy | 91.8 | — | Unverified |
| 7 | TransFG | Accuracy | 91.7 | — | Unverified |
| 8 | ViT-NeT | Accuracy | 91.7 | — | Unverified |
| 9 | SWAG (ViT H/14) | Accuracy | 91.7 | — | Unverified |
| 10 | FFVT | Accuracy | 91.6 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MetaFormer (MetaFormer-2,384) | Accuracy | 93 | — | Unverified |
| 2 | HERBS | Accuracy | 93 | — | Unverified |
| 3 | PIM | Accuracy | 92.8 | — | Unverified |
| 4 | ViT-NeT (SwinV2-B) | Accuracy | 92.5 | — | Unverified |
| 5 | MPSA | Accuracy | 92.5 | — | Unverified |
| 6 | CSQA-Net | Accuracy | 92.3 | — | Unverified |
| 7 | I2-HOFI | Accuracy | 92.12 | — | Unverified |
| 8 | MDCM | Accuracy | 92 | — | Unverified |
| 9 | CGL | Accuracy | 91.7 | — | Unverified |
| 10 | SR-GNN | Accuracy | 91.2 | — | Unverified |