# Image Classification on CIFAR-10-LT λ=200 (test)

Source: [Image Classification on CIFAR-10-LT λ=200 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-200-test>)

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

Data updated: 2026-02-26T05:42:16.880Z

Evaluation of Image Classification performance on the CIFAR-10 Long Tail (LT) dataset configured with an imbalance ratio (lambda) of 200, using the test split.

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 λ=200 (test) |
| Metric | Error Rate |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 11 of 11 |
| 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

- [Error Rate](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-200-test.md?metric=Error%20Rate>): Lower is better; unit: PERCENT.

- [Error Rate @ 80% TPR](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-200-test.md?metric=Error%20Rate%20%40%2080%25%20TPR>): Lower is better; unit: PERCENT.

- [Error Rate @ 90% TPR](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-200-test.md?metric=Error%20Rate%20%40%2090%25%20TPR>): Lower is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-200-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Error Rate | Result date | Report paper |
| --- | --- | --- | --- |
| MetaSAug with cross-entropy loss | 23.11 | Not recorded | 68fa6bbe1e209131cea3008c |
| RISDA | 26 | Not recorded | 68fa6bbe1e209131cea3008c |
| Meta-class-weight with cross-entropy loss | 29.34 | Not recorded | 68fa6bbe1e209131cea3008c |
| Class-balanced CE | 31.23 | Not recorded | 68fa6bbe1e209131cea3008c |
| Meta-weight net | 32.8 | Not recorded | 68fa6bbe1e209131cea3008c |
| L2RW | 33.75 | Not recorded | 68fa6bbe1e209131cea3008c |
| Class-balanced fine-tuning | 33.76 | Not recorded | 68fa6bbe1e209131cea3008c |
| Cross-Entropy | 34.13 | Not recorded | 68fa6bbe1e209131cea3008c |

### MetaSAug with cross-entropy loss

Error Rate: 23.11. Result ID: 698ea228ffc3901de09f5260.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea2357d.md>)

[Implementation](<https://github.com/BIT-DA/MetaSAug>)

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

### RISDA

Error Rate: 26. Result ID: 698ea228ffc3901de09f5261.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.md>)

[Implementation](<https://github.com/xiaohua-chen/RISDA>)

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

### Meta-class-weight with cross-entropy loss

Error Rate: 29.34. Result ID: 698ea228ffc3901de09f525f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67401e209131cea1539a.md>)

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

### Class-balanced CE

Error Rate: 31.23. Result ID: 698ea228ffc3901de09f525c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.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.

### Meta-weight net

Error Rate: 32.8. Result ID: 698ea228ffc3901de09f525e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.md>)

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

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

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

### L2RW

Error Rate: 33.75. Result ID: 698ea228ffc3901de09f525b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65be1e209131cea0c1af.md>)

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

### Class-balanced fine-tuning

Error Rate: 33.76. Result ID: 698ea228ffc3901de09f525d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa647b1e209131cea04b2b.md>)

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

### Cross-Entropy

Error Rate: 34.13. Result ID: 698ea228ffc3901de09f525a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea3008c.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.