# Object Classification on Photo-Art-50 (test)

Source: [Object Classification on Photo-Art-50 (test)](<https://www.sota2.com/research/sota/object-classification-on-photo-art-50-test>)

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

Data updated: 2026-02-26T05:54:23.193Z

Evaluation of Object Classification performance on the test split of the Photo-Art-50 dataset, reporting overall, art-specific, and photo-specific 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 | Object Classification |
| Dataset (including any stated split) | Photo-Art-50 (test) |
| Metric | Overall Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Overall Accuracy](<https://www.sota2.com/research/sota/object-classification-on-photo-art-50-test.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

- [Art Accuracy](<https://www.sota2.com/research/sota/object-classification-on-photo-art-50-test.md?metric=Art%20Accuracy>): Higher is better; unit: PERCENT.

- [Photo Accuracy](<https://www.sota2.com/research/sota/object-classification-on-photo-art-50-test.md?metric=Photo%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SwiDeN | 94.42 | Not recorded | 68fa62a41e209131ce9fa827 |
| Baseline | 93.8 | Not recorded | 68fa62a41e209131ce9fa827 |
| GRN | 92.64 | Not recorded | 68fa62a41e209131ce9fa827 |

### SwiDeN

Overall Accuracy: 94.42. Result ID: 698bdf0eecace47ef5596860.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62a41e209131ce9fa827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a41e209131ce9fa827.md>)

[Implementation](<https://github.com/val-iisc/swiden>)

Recorded evaluation configuration: {"Evaluation Protocol":"5-crop pooling","Architecture":"C4-S"}. This record does not assert independent reproduction.

### Baseline

Overall Accuracy: 93.8. Result ID: 698bdf0decace47ef559685e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62a41e209131ce9fa827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61d01e209131ce9f62f5.md>)

[Implementation](<http://www.robots.ox.ac.uk/~vgg/research/very_deep/>)

Recorded evaluation configuration: {"Evaluation Protocol":"5-crop pooling"}. This record does not assert independent reproduction.

### GRN

Overall Accuracy: 92.64. Result ID: 698bdf0eecace47ef559685f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62a41e209131ce9fa827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61b71e209131ce9f5a50.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"5-crop pooling"}. This record does not assert independent reproduction.

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