# Image Classification on SVHN (Metrics: CA, BA, ASR)

Source: [Image Classification on SVHN (Metrics: CA, BA, ASR)](<https://www.sota2.com/research/sota/image-classification-on-svhn-metrics-ca-ba-asr>)

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

Data updated: 2026-03-04T20:21:39.398Z

Evaluation of Image Classification performance on the SVHN dataset, reporting Classification Accuracy (CA), Balanced Accuracy (BA), and Average Score Rate (ASR).

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) | SVHN |
| Metric | Balanced Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [Balanced Accuracy](<https://www.sota2.com/research/sota/image-classification-on-svhn-metrics-ca-ba-asr.md?metric=Balanced%20Accuracy>): Higher is better; unit: PERCENT.

- [Classification Accuracy](<https://www.sota2.com/research/sota/image-classification-on-svhn-metrics-ca-ba-asr.md?metric=Classification%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Score Rate](<https://www.sota2.com/research/sota/image-classification-on-svhn-metrics-ca-ba-asr.md?metric=Average%20Score%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Balanced Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DSBA | 72.18 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| WaNet | 71.43 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| GhostEncoder | 68.42 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| GhostEncoder | 65.14 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| DSBA | 64.74 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| CTRL | 61.95 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| IMPERATIVE | 60.48 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| DSBA | 60.16 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| IMPERATIVE | 60.13 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| CTRL | 58.24 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| IMPERATIVE | 56.42 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| CTRL | 55.78 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| WaNet | 55.75 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| WaNet | 54.56 | Not recorded | 69a7bc7d2d603e6de3e3d462 |
| GhostEncoder | 52.48 | Not recorded | 69a7bc7d2d603e6de3e3d462 |

### DSBA

Balanced Accuracy: 72.18. Result ID: 69a8944f6dbb7075b9514d95.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"Tiny-ImageNet"}. This record does not assert independent reproduction.

### WaNet

Balanced Accuracy: 71.43. Result ID: 69a8944f6dbb7075b9514d91.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa696b1e209131cea21e53.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"Tiny-ImageNet"}. This record does not assert independent reproduction.

### GhostEncoder

Balanced Accuracy: 68.42. Result ID: 69a8944f6dbb7075b9514d93.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbb6.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"Tiny-ImageNet"}. This record does not assert independent reproduction.

### GhostEncoder

Balanced Accuracy: 65.14. Result ID: 69a8944f6dbb7075b9514d87.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbb6.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"CIFAR-10"}. This record does not assert independent reproduction.

### DSBA

Balanced Accuracy: 64.74. Result ID: 69a8944f6dbb7075b9514d89.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"CIFAR-10"}. This record does not assert independent reproduction.

### CTRL

Balanced Accuracy: 61.95. Result ID: 69a8944f6dbb7075b9514d92.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705b1e209131cea4a910.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"Tiny-ImageNet"}. This record does not assert independent reproduction.

### IMPERATIVE

Balanced Accuracy: 60.48. Result ID: 69a8944f6dbb7075b9514d94.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"Tiny-ImageNet"}. This record does not assert independent reproduction.

### DSBA

Balanced Accuracy: 60.16. Result ID: 69a8944f6dbb7075b9514d8f.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"STL-10"}. This record does not assert independent reproduction.

### IMPERATIVE

Balanced Accuracy: 60.13. Result ID: 69a8944f6dbb7075b9514d8e.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"STL-10"}. This record does not assert independent reproduction.

### CTRL

Balanced Accuracy: 58.24. Result ID: 69a8944f6dbb7075b9514d86.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705b1e209131cea4a910.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"CIFAR-10"}. This record does not assert independent reproduction.

### IMPERATIVE

Balanced Accuracy: 56.42. Result ID: 69a8944f6dbb7075b9514d88.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"CIFAR-10"}. This record does not assert independent reproduction.

### CTRL

Balanced Accuracy: 55.78. Result ID: 69a8944f6dbb7075b9514d8c.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705b1e209131cea4a910.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"STL-10"}. This record does not assert independent reproduction.

### WaNet

Balanced Accuracy: 55.75. Result ID: 69a8944f6dbb7075b9514d85.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa696b1e209131cea21e53.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"CIFAR-10"}. This record does not assert independent reproduction.

### WaNet

Balanced Accuracy: 54.56. Result ID: 69a8944f6dbb7075b9514d8b.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa696b1e209131cea21e53.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"STL-10"}. This record does not assert independent reproduction.

### GhostEncoder

Balanced Accuracy: 52.48. Result ID: 69a8944f6dbb7075b9514d8d.

[Reporting paper](<https://www.sota2.com/research/paper/69a7bc7d2d603e6de3e3d462.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbb6.md>)

Recorded evaluation configuration: {"Pre-training Dataset":"STL-10"}. This record does not assert independent reproduction.

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