# Fine-grained image classification on FGVC Aircraft (test)

Source: [Fine-grained image classification on FGVC Aircraft (test)](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-fgvc-aircraft-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-02T13:41:37.736Z

Evaluation of Fine-grained Image Classification performance on the test split of the FGVC Aircraft dataset, reporting Base, Novel, and Harmonic Mean accuracies.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Fine-grained image classification |
| Dataset (including any stated split) | FGVC Aircraft (test) |
| Metric | Base Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Base Accuracy](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-fgvc-aircraft-test.md?metric=Base%20Accuracy>): Higher is better; unit: PERCENT.

- [Novel Accuracy](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-fgvc-aircraft-test.md?metric=Novel%20Accuracy>): Higher is better; unit: PERCENT.

- [Harmonic Mean Accuracy](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-fgvc-aircraft-test.md?metric=Harmonic%20Mean%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Base Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ToolFG | 75.6 | Not recorded | 6a1e6454dbd7150506f859f6 |
| DiVE-k | 68.1 | Not recorded | 6a1e6454dbd7150506f859f6 |
| Fine-R1 | 66.8 | Not recorded | 6a1e6454dbd7150506f859f6 |
| ViRFT | 66.4 | Not recorded | 6a1e6454dbd7150506f859f6 |
| Qwen2.5-VL-7B | 50.3 | Not recorded | 6a1e6454dbd7150506f859f6 |
| PromptSRC | 42.7 | Not recorded | 6a1e6454dbd7150506f859f6 |
| MaPLe | 37.4 | Not recorded | 6a1e6454dbd7150506f859f6 |

### ToolFG

Base Accuracy: 75.6. Result ID: 6a1edd74fbc373592c1b08f9.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6454dbd7150506f859f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e6454dbd7150506f859f6.md>)

Recorded evaluation configuration: {"Training Strategy":"per-dataset training","Evaluation Protocol":"Zero-shot base-to-novel generalization"}. This record does not assert independent reproduction.

### DiVE-k

Base Accuracy: 68.1. Result ID: 6a1edd74fbc373592c1b08f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6454dbd7150506f859f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69253806d6b0dd334292f3a4.md>)

Recorded evaluation configuration: {"Training Strategy":"per-dataset training","Evaluation Protocol":"Zero-shot base-to-novel generalization"}. This record does not assert independent reproduction.

### Fine-R1

Base Accuracy: 66.8. Result ID: 6a1edd74fbc373592c1b08f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6454dbd7150506f859f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abb81c97a0b3e3b5ddf45.md>)

Recorded evaluation configuration: {"Training Strategy":"per-dataset training","Evaluation Protocol":"Zero-shot base-to-novel generalization"}. This record does not assert independent reproduction.

### ViRFT

Base Accuracy: 66.4. Result ID: 6a1edd74fbc373592c1b08f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6454dbd7150506f859f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77381e209131cea71c39.md>)

Recorded evaluation configuration: {"Training Strategy":"per-dataset training","Evaluation Protocol":"Zero-shot base-to-novel generalization"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Base Accuracy: 50.3. Result ID: 6a1edd74fbc373592c1b08f3.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6454dbd7150506f859f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"Training Strategy":"per-dataset training","Evaluation Protocol":"Zero-shot base-to-novel generalization"}. This record does not assert independent reproduction.

### PromptSRC

Base Accuracy: 42.7. Result ID: 6a1edd74fbc373592c1b08f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6454dbd7150506f859f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705e1e209131cea4aa58.md>)

Recorded evaluation configuration: {"Training Strategy":"per-dataset training","Evaluation Protocol":"Zero-shot base-to-novel generalization"}. This record does not assert independent reproduction.

### MaPLe

Base Accuracy: 37.4. Result ID: 6a1edd74fbc373592c1b08f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6454dbd7150506f859f6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef21e209131cea4311c.md>)

[Implementation](<https://github.com/muzairkhattak/multimodal-prompt-learning>)

Recorded evaluation configuration: {"Training Strategy":"per-dataset training","Evaluation Protocol":"Zero-shot base-to-novel generalization"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
