# Image Classification on CIFAR100 mu=1 (test)

Source: [Image Classification on CIFAR100 mu=1 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar100-mu-1-test>)

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

Data updated: 2026-02-26T05:27:07.800Z

Evaluation of Image Classification performance on the test split of the CIFAR-100 dataset configured with the mu=1 setting (indicating a specific noise level or perturbation).

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) | CIFAR100 mu=1 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar100-mu-1-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GDW | 70.65 | Not recorded | 68fa58a01e209131ce9afc20 |
| MWNet | 70.64 | Not recorded | 68fa58a01e209131ce9afc20 |
| Balanced | 70.56 | Not recorded | 68fa58a01e209131ce9afc20 |
| Fine-tuning | 70.52 | Not recorded | 68fa58a01e209131ce9afc20 |
| INSW | 70.52 | Not recorded | 68fa58a01e209131ce9afc20 |
| BaseModel | 70.42 | Not recorded | 68fa58a01e209131ce9afc20 |
| Focal | 68.48 | Not recorded | 68fa58a01e209131ce9afc20 |
| L2RW | 63.4 | Not recorded | 68fa58a01e209131ce9afc20 |

### GDW

Accuracy: 70.65. Result ID: 698ba3cf7a967eddb7703d6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

[Implementation](<https://github.com/GGchen1997/GDW-NIPS2021>)

Recorded evaluation configuration: {"imbalance ratio (mu)":"1"}. This record does not assert independent reproduction.

### MWNet

Accuracy: 70.64. Result ID: 698ba3cf7a967eddb7703d6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66791e209131cea1067e.md>)

[Implementation](<https://github.com/xjtushujun/meta-weight-net>)

Recorded evaluation configuration: {"imbalance ratio (mu)":"1"}. This record does not assert independent reproduction.

### Balanced

Accuracy: 70.56. Result ID: 698ba3cf7a967eddb7703d6a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa654f1e209131cea0988a.md>)

[Implementation](<https://github.com/richardaecn/class-balanced-loss>)

Recorded evaluation configuration: {"imbalance ratio (mu)":"1"}. This record does not assert independent reproduction.

### Fine-tuning

Accuracy: 70.52. Result ID: 698ba3cf7a967eddb7703d68.

[Reporting paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

Recorded evaluation configuration: {"imbalance ratio (mu)":"1"}. This record does not assert independent reproduction.

### INSW

Accuracy: 70.52. Result ID: 698ba3cf7a967eddb7703d6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66911e209131cea10efa.md>)

Recorded evaluation configuration: {"imbalance ratio (mu)":"1"}. This record does not assert independent reproduction.

### BaseModel

Accuracy: 70.42. Result ID: 698ba3cf7a967eddb7703d67.

[Reporting paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

Recorded evaluation configuration: {"imbalance ratio (mu)":"1"}. This record does not assert independent reproduction.

### Focal

Accuracy: 68.48. Result ID: 698ba3cf7a967eddb7703d69.

[Reporting paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa640c1e209131cea02556.md>)

[Implementation](<https://github.com/facebookresearch/Detectron>)

Recorded evaluation configuration: {"imbalance ratio (mu)":"1"}. This record does not assert independent reproduction.

### L2RW

Accuracy: 63.4. Result ID: 698ba3cf7a967eddb7703d6b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa58a01e209131ce9afc20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66791e209131cea1067e.md>)

[Implementation](<https://github.com/xjtushujun/meta-weight-net>)

Recorded evaluation configuration: {"imbalance ratio (mu)":"1"}. This record does not assert independent reproduction.

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