# Fine-grained Image Classification on CUB Indigo Bunting vs. Blue Grosbeak 2011 (test)

Source: [Fine-grained Image Classification on CUB Indigo Bunting vs. Blue Grosbeak 2011 (test)](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-cub-indigo-bunting-vs-blue-grosbeak-2011-test>)

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

Data updated: 2026-07-07T11:02:25.630Z

Evaluation of fine-grained classification performance specifically comparing the Indigo Bunting and Blue Grosbeak species on the test split of the CUB dataset, utilizing concept similarity and class-specific accuracy metrics.

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) | CUB Indigo Bunting vs. Blue Grosbeak 2011 (test) |
| Metric | Average Accuracy (Indigo Bunting) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Average Accuracy (Indigo Bunting)](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-cub-indigo-bunting-vs-blue-grosbeak-2011-test.md?metric=Average%20Accuracy%20(Indigo%20Bunting)>): Higher is better; unit: PERCENT.

- [Average Cross-Model Concept Cosine Similarity](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-cub-indigo-bunting-vs-blue-grosbeak-2011-test.md?metric=Average%20Cross-Model%20Concept%20Cosine%20Similarity>): Higher is better; unit: SCALAR.

- [Average Accuracy (Blue Grosbeak)](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-cub-indigo-bunting-vs-blue-grosbeak-2011-test.md?metric=Average%20Accuracy%20(Blue%20Grosbeak)>): Higher is better; unit: PERCENT.

- [Accuracy Gap (Indigo Bunting - Blue Grosbeak)](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-cub-indigo-bunting-vs-blue-grosbeak-2011-test.md?metric=Accuracy%20Gap%20(Indigo%20Bunting%20-%20Blue%20Grosbeak)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Average Accuracy (Indigo Bunting) | Result date | Report paper |
| --- | --- | --- | --- |
| Rashomon-Slice | 92 | Not recorded | 692689e8d6b0dd33429306a2 |
| Random Init | 88.67 | Not recorded | 692689e8d6b0dd33429306a2 |
| DivEnsemble | 86.67 | Not recorded | 692689e8d6b0dd33429306a2 |
| Dropout | 82.67 | Not recorded | 692689e8d6b0dd33429306a2 |

### Rashomon-Slice

Average Accuracy (Indigo Bunting): 92. Result ID: 6a4cdcaf60b88bb339cb2585.

[Reporting paper](<https://www.sota2.com/research/paper/692689e8d6b0dd33429306a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692689e8d6b0dd33429306a2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Random Init

Average Accuracy (Indigo Bunting): 88.67. Result ID: 6a4cdcaf60b88bb339cb2582.

[Reporting paper](<https://www.sota2.com/research/paper/692689e8d6b0dd33429306a2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DivEnsemble

Average Accuracy (Indigo Bunting): 86.67. Result ID: 6a4cdcaf60b88bb339cb2584.

[Reporting paper](<https://www.sota2.com/research/paper/692689e8d6b0dd33429306a2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Dropout

Average Accuracy (Indigo Bunting): 82.67. Result ID: 6a4cdcaf60b88bb339cb2583.

[Reporting paper](<https://www.sota2.com/research/paper/692689e8d6b0dd33429306a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa720f1e209131cea543eb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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