# Image Classification on ImageNet B 2012 (val)

Source: [Image Classification on ImageNet B 2012 (val)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-b-2012-val>)

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

Data updated: 2026-05-14T06:58:29.945Z

Evaluation of Image Classification performance on the validation split of the ImageNet B 2012 dataset, reporting metrics such as Estimated Accuracy and Area Under the Precision-Recall Curve (AUPR).

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) | ImageNet B 2012 (val) |
| Metric | Estimated Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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

- [Estimated Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-b-2012-val.md?metric=Estimated%20Accuracy>): Higher is better; unit: PERCENT.

- [AUPR](<https://www.sota2.com/research/sota/image-classification-on-imagenet-b-2012-val.md?metric=AUPR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Estimated Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TS | 80.86 | Not recorded | 68fa67d21e209131cea18b0c |
| TS | 80.44 | Not recorded | 68fa67d21e209131cea18b0c |
| MP\* | 76.38 | Not recorded | 68fa67d21e209131cea18b0c |
| MP\* | 75.39 | Not recorded | 68fa67d21e209131cea18b0c |
| Entropy | 71.31 | Not recorded | 68fa67d21e209131cea18b0c |
| MP | 70.04 | Not recorded | 68fa67d21e209131cea18b0c |
| MP | 67.57 | Not recorded | 68fa67d21e209131cea18b0c |
| Entropy | 66.94 | Not recorded | 68fa67d21e209131cea18b0c |
| DIVER | 28.7 | Not recorded | 6a055714dbc836b87d828c8b |
| DIVER | 27.8 | Not recorded | 6a055714dbc836b87d828c8b |
| DIVER | 26.1 | Not recorded | 6a055714dbc836b87d828c8b |
| GLaD | 23.7 | Not recorded | 6a055714dbc836b87d828c8b |
| GLaD | 22.5 | Not recorded | 6a055714dbc836b87d828c8b |
| DD | 21.3 | Not recorded | 6a055714dbc836b87d828c8b |
| DD | 21 | Not recorded | 6a055714dbc836b87d828c8b |
| GLaD | 20.1 | Not recorded | 6a055714dbc836b87d828c8b |
| DD | 16.7 | Not recorded | 6a055714dbc836b87d828c8b |

### TS

Estimated Accuracy: 80.86. Result ID: 698d48b08b517eb4332059d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638b1e209131ce9ff6d1.md>)

Recorded evaluation configuration: {"Target Model":"MobileNet"}. This record does not assert independent reproduction.

### TS

Estimated Accuracy: 80.44. Result ID: 698d48b08b517eb4332059d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638b1e209131ce9ff6d1.md>)

Recorded evaluation configuration: {"Target Model":"ResNet-50"}. This record does not assert independent reproduction.

### MP\*

Estimated Accuracy: 76.38. Result ID: 698d48b08b517eb4332059d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Target Model":"ResNet-50"}. This record does not assert independent reproduction.

### MP\*

Estimated Accuracy: 75.39. Result ID: 698d48b08b517eb4332059d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Target Model":"MobileNet"}. This record does not assert independent reproduction.

### Entropy

Estimated Accuracy: 71.31. Result ID: 698d48b08b517eb4332059d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

Recorded evaluation configuration: {"Target Model":"MobileNet"}. This record does not assert independent reproduction.

### MP

Estimated Accuracy: 70.04. Result ID: 698d48b08b517eb4332059cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Target Model":"MobileNet"}. This record does not assert independent reproduction.

### MP

Estimated Accuracy: 67.57. Result ID: 698d48b08b517eb4332059d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Target Model":"ResNet-50"}. This record does not assert independent reproduction.

### Entropy

Estimated Accuracy: 66.94. Result ID: 698d48b08b517eb4332059d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa67d21e209131cea18b0c.md>)

Recorded evaluation configuration: {"Target Model":"ResNet-50"}. This record does not assert independent reproduction.

### DIVER

Estimated Accuracy: 28.7. Result ID: 6a05729047f34ce924ebe6e9.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

Recorded evaluation configuration: {"Alg.":"MTT","IPC":"1"}. This record does not assert independent reproduction.

### DIVER

Estimated Accuracy: 27.8. Result ID: 6a05729047f34ce924ebe6e6.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

Recorded evaluation configuration: {"Alg.":"DC","IPC":"1"}. This record does not assert independent reproduction.

### DIVER

Estimated Accuracy: 26.1. Result ID: 6a05729047f34ce924ebe6e3.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

Recorded evaluation configuration: {"Alg.":"DM","IPC":"1"}. This record does not assert independent reproduction.

### GLaD

Estimated Accuracy: 23.7. Result ID: 6a05729047f34ce924ebe6e5.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Alg.":"DC","IPC":"1"}. This record does not assert independent reproduction.

### GLaD

Estimated Accuracy: 22.5. Result ID: 6a05729047f34ce924ebe6e8.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Alg.":"MTT","IPC":"1"}. This record does not assert independent reproduction.

### DD

Estimated Accuracy: 21.3. Result ID: 6a05729047f34ce924ebe6e4.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f533.md>)

Recorded evaluation configuration: {"Alg.":"DC","IPC":"1"}. This record does not assert independent reproduction.

### DD

Estimated Accuracy: 21. Result ID: 6a05729047f34ce924ebe6e7.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f533.md>)

Recorded evaluation configuration: {"Alg.":"MTT","IPC":"1"}. This record does not assert independent reproduction.

### GLaD

Estimated Accuracy: 20.1. Result ID: 6a05729047f34ce924ebe6e2.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f311e209131cea44584.md>)

[Implementation](<https://georgecazenavette.github.io/glad/>)

Recorded evaluation configuration: {"Alg.":"DM","IPC":"1"}. This record does not assert independent reproduction.

### DD

Estimated Accuracy: 16.7. Result ID: 6a05729047f34ce924ebe6e1.

[Reporting paper](<https://www.sota2.com/research/paper/6a055714dbc836b87d828c8b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f533.md>)

Recorded evaluation configuration: {"Alg.":"DM","IPC":"1"}. This record does not assert independent reproduction.

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