# Image Classification on 11 Image Classification Datasets Average

Source: [Image Classification on 11 Image Classification Datasets Average](<https://www.sota2.com/research/sota/image-classification-on-11-image-classification-datasets-average>)

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

Data updated: 2026-02-26T05:36:02.303Z

Average performance of Image Classification models evaluated across a collection of 11 distinct datasets, reporting metrics including Average Accuracy (ACC), Average Number of Concepts, and Average CEA.

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) | 11 Image Classification Datasets Average |
| Metric | Avg ACC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Avg ACC](<https://www.sota2.com/research/sota/image-classification-on-11-image-classification-datasets-average.md?metric=Avg%20ACC>): Higher is better; unit: PERCENT.

- [Avg # Concepts](<https://www.sota2.com/research/sota/image-classification-on-11-image-classification-datasets-average.md?metric=Avg%20%23%20Concepts>): Higher is better; unit: SCALAR.

- [Avg CEA](<https://www.sota2.com/research/sota/image-classification-on-11-image-classification-datasets-average.md?metric=Avg%20CEA>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg ACC | Result date | Report paper |
| --- | --- | --- | --- |
| PS-CBM | 78.3 | Not recorded | 692d210bd6b0dd334293164b |
| DN-CBM | 77.3 | Not recorded | 692d210bd6b0dd334293164b |
| VLG-CBM | 75.2 | Not recorded | 692d210bd6b0dd334293164b |
| LM4CV | 73.4 | Not recorded | 692d210bd6b0dd334293164b |
| LF-CBM | 72.9 | Not recorded | 692d210bd6b0dd334293164b |
| LaBo | 72.8 | Not recorded | 692d210bd6b0dd334293164b |
| V2C-CBM | 72.8 | Not recorded | 692d210bd6b0dd334293164b |
| Res-CBM | 71.8 | Not recorded | 692d210bd6b0dd334293164b |
| DCBM | 70.9 | Not recorded | 692d210bd6b0dd334293164b |

### PS-CBM

Avg ACC: 78.3. Result ID: 6995e62b3badfaffe6ee3d84.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

Recorded evaluation configuration: {"Concept Generation":"Language+Vision","Concept Pools":"Partially Shared"}. This record does not assert independent reproduction.

### DN-CBM

Avg ACC: 77.3. Result ID: 6995e62b3badfaffe6ee3d7f.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74701e209131cea61cff.md>)

Recorded evaluation configuration: {"Concept Generation":"Vision","Concept Pools":"Globally Shared"}. This record does not assert independent reproduction.

### VLG-CBM

Avg ACC: 75.2. Result ID: 6995e62b3badfaffe6ee3d81.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769c1e209131cea6e1ca.md>)

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

### LM4CV

Avg ACC: 73.4. Result ID: 6995e62b3badfaffe6ee3d7e.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70471e209131cea4a234.md>)

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

### LF-CBM

Avg ACC: 72.9. Result ID: 6995e62b3badfaffe6ee3d7d.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa01e209131cea46b96.md>)

Recorded evaluation configuration: {"Concept Generation":"Language","Concept Pools":"Globally Shared"}. This record does not assert independent reproduction.

### LaBo

Avg ACC: 72.8. Result ID: 6995e62b3badfaffe6ee3d7c.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f231e209131cea43f60.md>)

Recorded evaluation configuration: {"Concept Generation":"Language","Concept Pools":"Independent"}. This record does not assert independent reproduction.

### V2C-CBM

Avg ACC: 72.8. Result ID: 6995e62b3badfaffe6ee3d82.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79941e209131cea7e642.md>)

Recorded evaluation configuration: {"Concept Generation":"Vision","Concept Pools":"Independent"}. This record does not assert independent reproduction.

### Res-CBM

Avg ACC: 71.8. Result ID: 6995e62b3badfaffe6ee3d80.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f41e209131cea598ce.md>)

[Implementation](<https://github.com/HelloSCM/Res-CBM>)

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

### DCBM

Avg ACC: 70.9. Result ID: 6995e62b3badfaffe6ee3d83.

[Reporting paper](<https://www.sota2.com/research/paper/692d210bd6b0dd334293164b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d11e209131cea7f8b9.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.