# Image Classification on CIFAR-100-LT (rho=100) (test)

Source: [Image Classification on CIFAR-100-LT (rho=100) (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-lt-rho-100-test>)

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

Data updated: 2026-02-26T05:28:38.045Z

Evaluation of Image Classification performance on the test split of the CIFAR-100 Long Tail dataset configured with an imbalance ratio (rho) of 100, reporting accuracy.

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-LT ($ ho=100$) (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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-lt-rho-100-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SMC | 48.9 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| CMO | 46.6 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| Remix | 45.8 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| TSC | 43.8 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| KCL | 42.8 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| LDAM-DRW | 42 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| CE-DRW | 40.5 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| CE-DRS | 40.4 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| BS-Focal | 39.6 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| LDAM | 39.6 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| BS | 38.6 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| Focal | 38.4 | Not recorded | 68fa6dfc1e209131cea3d2c0 |
| CE | 38.3 | Not recorded | 68fa6dfc1e209131cea3d2c0 |

### SMC

Accuracy: 48.9. Result ID: 698ffd773a6c314849fd4c16.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### CMO

Accuracy: 46.6. Result ID: 698ffd773a6c314849fd4c13.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea32354.md>)

[Implementation](<https://github.com/naver-ai/cmo>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### Remix

Accuracy: 45.8. Result ID: 698ffd773a6c314849fd4c12.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c41e209131cea1e3de.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### TSC

Accuracy: 43.8. Result ID: 698ffd773a6c314849fd4c15.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c741e209131cea33fe7.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### KCL

Accuracy: 42.8. Result ID: 698ffd773a6c314849fd4c14.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### LDAM-DRW

Accuracy: 42. Result ID: 698ffd773a6c314849fd4c11.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### CE-DRW

Accuracy: 40.5. Result ID: 698ffd773a6c314849fd4c0e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### CE-DRS

Accuracy: 40.4. Result ID: 698ffd773a6c314849fd4c0f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### BS-Focal

Accuracy: 39.6. Result ID: 698ffd773a6c314849fd4c0d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### LDAM

Accuracy: 39.6. Result ID: 698ffd773a6c314849fd4c10.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### BS

Accuracy: 38.6. Result ID: 698ffd773a6c314849fd4c0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### Focal

Accuracy: 38.4. Result ID: 698ffd773a6c314849fd4c0c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### CE

Accuracy: 38.3. Result ID: 698ffd773a6c314849fd4c0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2c0.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

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