# Image Classification on CIFAR-10-LT SADE Setting (test)

Source: [Image Classification on CIFAR-10-LT SADE Setting (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test>)

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

Data updated: 2026-02-26T05:45:30.616Z

Evaluation of Image Classification performance on the test split of the CIFAR-10 Long Tail (LT) dataset under the SADE setting, reporting metrics across forward, backward, and uniform sampling conditions.

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-10-LT SADE Setting (test) |
| Metric | Forward LT 100 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Forward LT 100 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Forward%20LT%20100%20Accuracy>): Higher is better; unit: PERCENT.

- [Forward LT 50 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Forward%20LT%2050%20Accuracy>): Higher is better; unit: PERCENT.

- [Forward LT 25 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Forward%20LT%2025%20Accuracy>): Higher is better; unit: PERCENT.

- [Forward LT 10 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Forward%20LT%2010%20Accuracy>): Higher is better; unit: PERCENT.

- [Forward LT 5 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Forward%20LT%205%20Accuracy>): Higher is better; unit: PERCENT.

- [Forward LT 2 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Forward%20LT%202%20Accuracy>): Higher is better; unit: PERCENT.

- [Uniform 1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Uniform%201%20Accuracy>): Higher is better; unit: PERCENT.

- [Backward LT 2 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Backward%20LT%202%20Accuracy>): Higher is better; unit: PERCENT.

- [Backward LT 5 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Backward%20LT%205%20Accuracy>): Higher is better; unit: PERCENT.

- [Backward LT 10 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Backward%20LT%2010%20Accuracy>): Higher is better; unit: PERCENT.

- [Backward LT 25 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Backward%20LT%2025%20Accuracy>): Higher is better; unit: PERCENT.

- [Backward LT 50 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Backward%20LT%2050%20Accuracy>): Higher is better; unit: PERCENT.

- [Backward LT 100 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Backward%20LT%20100%20Accuracy>): Higher is better; unit: PERCENT.

- [Mean Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-sade-setting-test.md?metric=Mean%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Forward LT 100 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| BalPoE | 92.13 | Not recorded | 68fa73321e209131cea5b138 |
| DirMixE | 90.92 | Not recorded | 68fa73321e209131cea5b138 |
| LDAM | 90.56 | Not recorded | 68fa73321e209131cea5b138 |
| SADE | 90.15 | Not recorded | 68fa73321e209131cea5b138 |
| LA | 89.79 | Not recorded | 68fa73321e209131cea5b138 |
| LADE | 87.45 | Not recorded | 68fa73321e209131cea5b138 |
| RIDE | 87.01 | Not recorded | 68fa73321e209131cea5b138 |
| DDC | 86.72 | Not recorded | 68fa73321e209131cea5b138 |
| VS | 84.26 | Not recorded | 68fa73321e209131cea5b138 |

### BalPoE

Forward LT 100 Accuracy: 92.13. Result ID: 6992cb4e3a6c314849118ad8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46df6.md>)

[Implementation](<https://github.com/emasa/BalPoE-CalibratedLT>)

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

### DirMixE

Forward LT 100 Accuracy: 90.92. Result ID: 6992cb4e3a6c314849118ad9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

[Implementation](<https://github.com/scongl/DirMixE>)

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

### LDAM

Forward LT 100 Accuracy: 90.56. Result ID: 6992cb4e3a6c314849118ad1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

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

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

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

### SADE

Forward LT 100 Accuracy: 90.15. Result ID: 6992cb4e3a6c314849118ad7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dc51e209131cea3c01a.md>)

[Implementation](<https://github.com/Vanint/SADE-AgnosticLT>)

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

### LA

Forward LT 100 Accuracy: 89.79. Result ID: 6992cb4e3a6c314849118ad2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a531e209131cea275d5.md>)

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

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

### LADE

Forward LT 100 Accuracy: 87.45. Result ID: 6992cb4e3a6c314849118ad4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Implementation](<https://github.com/hyperconnect/LADE>)

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

### RIDE

Forward LT 100 Accuracy: 87.01. Result ID: 6992cb4e3a6c314849118ad6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c7b1e209131cea3436b.md>)

[Implementation](<https://github.com/frank-xwang/RIDE-LongTailRecognition>)

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

### DDC

Forward LT 100 Accuracy: 86.72. Result ID: 6992cb4e3a6c314849118ad5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

### VS

Forward LT 100 Accuracy: 84.26. Result ID: 6992cb4e3a6c314849118ad3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73321e209131cea5b138.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2ccda.md>)

[Implementation](<https://github.com/orparask/VS-Loss>)

Recorded evaluation configuration: {"Evaluation Protocol":"SADE's Setting"}. This record does not assert independent reproduction.

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