# Image Classification on Caltech-UCSD Birds-200-2011 (CUB) Standard

Source: [Image Classification on Caltech-UCSD Birds-200-2011 (CUB) Standard](<https://www.sota2.com/research/sota/image-classification-on-caltech-ucsd-birds-200-2011-cub-standard>)

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

Data updated: 2026-02-26T05:46:31.475Z

Evaluation of standard Image Classification performance on the Caltech-UCSD Birds 200-2011 (CUB) dataset using the standard evaluation split/configuration.

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 | Image Classification |
| Dataset (including any stated split) | Caltech-UCSD Birds-200-2011 (CUB) Standard |
| Metric | Hit@1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Hit@1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-caltech-ucsd-birds-200-2011-cub-standard.md?metric=Hit%401%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Hit@1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DEM | 59 | Not recorded | 68fa66171e209131cea0e403 |
| DEM | 58.3 | Not recorded | 68fa66171e209131cea0e403 |
| DS-SJE | 56.8 | Not recorded | 68fa66171e209131cea0e403 |
| SynC-struct | 54.5 | Not recorded | 68fa66171e209131cea0e403 |
| DEM | 53.5 | Not recorded | 68fa66171e209131cea0e403 |
| SJE | 51.7 | Not recorded | 68fa66171e209131cea0e403 |
| DS-SJE | 50.4 | Not recorded | 68fa66171e209131cea0e403 |
| SJE | 50.1 | Not recorded | 68fa66171e209131cea0e403 |
| ESZSL | 47.2 | Not recorded | 68fa66171e209131cea0e403 |
| SEC-ML | 43.3 | Not recorded | 68fa66171e209131cea0e403 |
| JLSE | 42.1 | Not recorded | 68fa66171e209131cea0e403 |
| Socher et al. | 39.6 | Not recorded | 68fa66171e209131cea0e403 |
| Ba et al. | 34 | Not recorded | 68fa66171e209131cea0e403 |
| DeViSE | 33.5 | Not recorded | 68fa66171e209131cea0e403 |
| MTMDL | 32.3 | Not recorded | 68fa66171e209131cea0e403 |
| SSE-ReLU | 30.4 | Not recorded | 68fa66171e209131cea0e403 |

### DEM

Hit@1 Accuracy: 59. Result ID: 698cd9a78b517eb4331d2bec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Implementation](<https://github.com/lzrobots/DeepEmbeddingModel_ZSL>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Attribute + Sentence description"}. This record does not assert independent reproduction.

### DEM

Hit@1 Accuracy: 58.3. Result ID: 698cd9a78b517eb4331d2bea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Implementation](<https://github.com/lzrobots/DeepEmbeddingModel_ZSL>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Attribute"}. This record does not assert independent reproduction.

### DS-SJE

Hit@1 Accuracy: 56.8. Result ID: 698cd9a78b517eb4331d2be9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa627a1e209131ce9f96e5.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Sentence description"}. This record does not assert independent reproduction.

### SynC-struct

Hit@1 Accuracy: 54.5. Result ID: 698cd9a78b517eb4331d2be2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62861e209131ce9f9e6e.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"GoogLeNet","Semantic Space (SS)":"Attribute"}. This record does not assert independent reproduction.

### DEM

Hit@1 Accuracy: 53.5. Result ID: 698cd9a78b517eb4331d2beb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Implementation](<https://github.com/lzrobots/DeepEmbeddingModel_ZSL>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Sentence description"}. This record does not assert independent reproduction.

### SJE

Hit@1 Accuracy: 51.7. Result ID: 698cd9a78b517eb4331d2bde.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62641e209131ce9f90f8.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"GoogLeNet","Semantic Space (SS)":"Attribute + Word vector"}. This record does not assert independent reproduction.

### DS-SJE

Hit@1 Accuracy: 50.4. Result ID: 698cd9a78b517eb4331d2be8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa627a1e209131ce9f96e5.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Attribute"}. This record does not assert independent reproduction.

### SJE

Hit@1 Accuracy: 50.1. Result ID: 698cd9a78b517eb4331d2bdd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62641e209131ce9f90f8.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"GoogLeNet","Semantic Space (SS)":"Attribute"}. This record does not assert independent reproduction.

### ESZSL

Hit@1 Accuracy: 47.2. Result ID: 698cd9a78b517eb4331d2bdf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"GoogLeNet","Semantic Space (SS)":"Attribute"}. This record does not assert independent reproduction.

### SEC-ML

Hit@1 Accuracy: 43.3. Result ID: 698cd9a78b517eb4331d2be3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa53041e209131ce97fb48.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"VGG net","Semantic Space (SS)":"Attribute"}. This record does not assert independent reproduction.

### JLSE

Hit@1 Accuracy: 42.1. Result ID: 698cd9a78b517eb4331d2be1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62b81e209131ce9fad7b.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"VGG net","Semantic Space (SS)":"Attribute"}. This record does not assert independent reproduction.

### Socher et al.

Hit@1 Accuracy: 39.6. Result ID: 698cd9a78b517eb4331d2be5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa60d81e209131ce9f15bd.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Attribute / Word vector"}. This record does not assert independent reproduction.

### Ba et al.

Hit@1 Accuracy: 34. Result ID: 698cd9a78b517eb4331d2be7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62191e209131ce9f79c3.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Attribute / Word vector"}. This record does not assert independent reproduction.

### DeViSE

Hit@1 Accuracy: 33.5. Result ID: 698cd9a78b517eb4331d2be4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Attribute / Word vector"}. This record does not assert independent reproduction.

### MTMDL

Hit@1 Accuracy: 32.3. Result ID: 698cd9a78b517eb4331d2be6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61ca1e209131ce9f5e8e.md>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"Inception-V2","Semantic Space (SS)":"Attribute / Word vector"}. This record does not assert independent reproduction.

### SSE-ReLU

Hit@1 Accuracy: 30.4. Result ID: 698cd9a78b517eb4331d2be0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa66171e209131cea0e403.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62191e209131ce9f79fe.md>)

[Implementation](<https://zimingzhang.wordpress.com/source-code/>)

Recorded evaluation configuration: {"Visual Feature Space (F)":"VGG net","Semantic Space (SS)":"Attribute"}. This record does not assert independent reproduction.

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