# Image Classification on CIFAR-100 ST-100 step-imbalance (test)

Source: [Image Classification on CIFAR-100 ST-100 step-imbalance (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-st-100-step-imbalance-test>)

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

Data updated: 2026-06-23T11:56:36.352Z

Evaluation of Image Classification performance on the test split of the CIFAR-100 dataset configured with ST-100 step-wise imbalance, reporting Accuracy and Standard Deviation.

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) | CIFAR-100 ST-100 step-imbalance (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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-cifar-100-st-100-step-imbalance-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Standard Deviation](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-st-100-step-imbalance-test.md?metric=Standard%20Deviation>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GRAIN | 60.17 | Not recorded | 6a3a13ac206542251d7c77c2 |
| SAM | 58.5 | Not recorded | 6a3a13ac206542251d7c77c2 |
| FocalLoss | 57.19 | Not recorded | 6a3a13ac206542251d7c77c2 |
| NoisyTune | 57.17 | Not recorded | 6a3a13ac206542251d7c77c2 |
| ViT (FFT) | 56.73 | Not recorded | 6a3a13ac206542251d7c77c2 |
| PCGrad | 50.01 | Not recorded | 6a3a13ac206542251d7c77c2 |
| SWA | 35.62 | Not recorded | 6a3a13ac206542251d7c77c2 |

### GRAIN

Accuracy: 60.17. Result ID: 6a3a7459fbc373592c384ce5.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13ac206542251d7c77c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a13ac206542251d7c77c2.md>)

Recorded evaluation configuration: {"Backbone":"ViT-base","Fine-tuning strategy":"FFT + GRAIN"}. This record does not assert independent reproduction.

### SAM

Accuracy: 58.5. Result ID: 6a3a7459fbc373592c384ce3.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13ac206542251d7c77c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69d81e209131cea248fb.md>)

[Implementation](<https://github.com/google-research/sam>)

Recorded evaluation configuration: {"Backbone":"ViT-base","Fine-tuning strategy":"FFT + SAM"}. This record does not assert independent reproduction.

### FocalLoss

Accuracy: 57.19. Result ID: 6a3a7459fbc373592c384ce0.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13ac206542251d7c77c2.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-base","Fine-tuning strategy":"FFT + FocalLoss"}. This record does not assert independent reproduction.

### NoisyTune

Accuracy: 57.17. Result ID: 6a3a7459fbc373592c384ce1.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13ac206542251d7c77c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c0e1e209131cea31c02.md>)

Recorded evaluation configuration: {"Backbone":"ViT-base","Fine-tuning strategy":"FFT + NoisyTune"}. This record does not assert independent reproduction.

### ViT (FFT)

Accuracy: 56.73. Result ID: 6a3a7459fbc373592c384cdf.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13ac206542251d7c77c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0b1e209131cea25b04.md>)

[Implementation](<https://github.com/google-research/vision_transformer>)

Recorded evaluation configuration: {"Backbone":"ViT-base","Fine-tuning strategy":"FFT"}. This record does not assert independent reproduction.

### PCGrad

Accuracy: 50.01. Result ID: 6a3a7459fbc373592c384ce4.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13ac206542251d7c77c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68fb1e209131cea1f828.md>)

Recorded evaluation configuration: {"Backbone":"ViT-base","Fine-tuning strategy":"FFT + PCGrad"}. This record does not assert independent reproduction.

### SWA

Accuracy: 35.62. Result ID: 6a3a7459fbc373592c384ce2.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13ac206542251d7c77c2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65651e209131cea09f96.md>)

[Implementation](<https://github.com/timgaripov/swa>)

Recorded evaluation configuration: {"Backbone":"ViT-base","Fine-tuning strategy":"FFT + SWA"}. This record does not assert independent reproduction.

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