# Image Classification on CIFAR-20 Class-prior Shift 10 (test)

Source: [Image Classification on CIFAR-20 Class-prior Shift 10 (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-20-class-prior-shift-10-test>)

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

Data updated: 2026-02-26T05:51:50.753Z

Evaluation of Image Classification model performance on the test split of the CIFAR-20 dataset under the Class-prior Shift 10 condition.

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-20 Class-prior Shift 10 (test) |
| Metric | Mean 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

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

## Recorded results

| Method | Mean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GIW | 49.17 | Not recorded | 68fa71131e209131cea4f1d5 |
| R-DIW | 45.19 | Not recorded | 68fa71131e209131cea4f1d5 |
| MW-Net | 44.96 | Not recorded | 68fa71131e209131cea4f1d5 |
| Reweight | 42.25 | Not recorded | 68fa71131e209131cea4f1d5 |
| DIW | 39.68 | Not recorded | 68fa71131e209131cea4f1d5 |
| Pretrain-val | 37.31 | Not recorded | 68fa71131e209131cea4f1d5 |
| Val-only | 28.45 | Not recorded | 68fa71131e209131cea4f1d5 |

### GIW

Mean Accuracy: 49.17. Result ID: 69917c183a6c3148490875c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1d5.md>)

[Implementation](<https://github.com/TongtongFANG/GIW>)

Recorded evaluation configuration: {"Shift type":"Class-prior Shift","Shift intensity":10,"Case":"iii","Trials":5}. This record does not assert independent reproduction.

### R-DIW

Mean Accuracy: 45.19. Result ID: 69917c183a6c3148490875c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa4f331e209131ce961818.md>)

Recorded evaluation configuration: {"Shift type":"Class-prior Shift","Shift intensity":10,"Case":"iii","Trials":5}. This record does not assert independent reproduction.

### MW-Net

Mean Accuracy: 44.96. Result ID: 69917c183a6c3148490875c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1d5.md>)

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

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

Recorded evaluation configuration: {"Shift type":"Class-prior Shift","Shift intensity":10,"Case":"iii","Trials":5}. This record does not assert independent reproduction.

### Reweight

Mean Accuracy: 42.25. Result ID: 69917c183a6c3148490875c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1d5.md>)

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

Recorded evaluation configuration: {"Shift type":"Class-prior Shift","Shift intensity":10,"Case":"iii","Trials":5}. This record does not assert independent reproduction.

### DIW

Mean Accuracy: 39.68. Result ID: 69917c183a6c3148490875c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1d5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a61e209131cea1d6bc.md>)

Recorded evaluation configuration: {"Shift type":"Class-prior Shift","Shift intensity":10,"Case":"iii","Trials":5}. This record does not assert independent reproduction.

### Pretrain-val

Mean Accuracy: 37.31. Result ID: 69917c183a6c3148490875c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1d5.md>)

Recorded evaluation configuration: {"Shift type":"Class-prior Shift","Shift intensity":10,"Case":"iii","Trials":5}. This record does not assert independent reproduction.

### Val-only

Mean Accuracy: 28.45. Result ID: 69917c183a6c3148490875c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1d5.md>)

Recorded evaluation configuration: {"Shift type":"Class-prior Shift","Shift intensity":10,"Case":"iii","Trials":5}. This record does not assert independent reproduction.

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