# Image Classification on STL10 Long-Tailed (gamma\_l=10, Nl=150, M=100k) (test)

Source: [Image Classification on STL10 Long-Tailed (gamma\_l=10, Nl=150, M=100k) (test)](<https://www.sota2.com/research/sota/image-classification-on-stl10-long-tailed-gamma_l-10-nl-150-m-100k-test>)

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

Data updated: 2026-02-26T05:28:19.924Z

Evaluation of Image Classification performance on a specific long-tailed test split of the STL-10 dataset, characterized by imbalance factor gamma\_l=10 and specific population sizes (Nl=150, M=100k).

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) | STL10 (Nl=150, M=100k, γl=10) long-tailed (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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-stl10-long-tailed-gamma_l-10-nl-150-m-100k-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FixMatch + LA + DASO | 71.3 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch + CB re-weight + DASO | 70.2 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch + DASO | 70 | Not recorded | 68fa6cb71e209131cea3583a |
| USADTM | 68.9 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch + DARP | 66.9 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch + BOSS | 66.4 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch + Logit Adjustment (LA) | 63.4 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch + CReST | 61.7 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch + CReST+ | 61.2 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch + CB re-weight | 58.9 | Not recorded | 68fa6cb71e209131cea3583a |
| FixMatch | 56.1 | Not recorded | 68fa6cb71e209131cea3583a |
| Logit Adjustment (LA) | 42.8 | Not recorded | 68fa6cb71e209131cea3583a |
| PseudoLabel | 42.3 | Not recorded | 68fa6cb71e209131cea3583a |
| LDAM-DRW | 41.8 | Not recorded | 68fa6cb71e209131cea3583a |
| cRT | 40.8 | Not recorded | 68fa6cb71e209131cea3583a |
| Supervised | 40.2 | Not recorded | 68fa6cb71e209131cea3583a |

### FixMatch + LA + DASO

Accuracy: 71.3. Result ID: 698f342f3a6c314849f6f9da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Implementation](<https://github.com/ytaek-oh/daso>)

Recorded evaluation configuration: {"SSL":true,"LB":true,"PB":true}. This record does not assert independent reproduction.

### FixMatch + CB re-weight + DASO

Accuracy: 70.2. Result ID: 698f342f3a6c314849f6f9d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Implementation](<https://github.com/ytaek-oh/daso>)

Recorded evaluation configuration: {"SSL":true,"LB":true,"PB":true}. This record does not assert independent reproduction.

### FixMatch + DASO

Accuracy: 70. Result ID: 698f342f3a6c314849f6f9d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Implementation](<https://github.com/ytaek-oh/daso>)

Recorded evaluation configuration: {"SSL":true,"LB":false,"PB":true}. This record does not assert independent reproduction.

### USADTM

Accuracy: 68.9. Result ID: 698f342f3a6c314849f6f9d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa687d1e209131cea1c486.md>)

Recorded evaluation configuration: {"SSL":true,"LB":false,"PB":true}. This record does not assert independent reproduction.

### FixMatch + DARP

Accuracy: 66.9. Result ID: 698f342f3a6c314849f6f9d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ab31e209131cea29d57.md>)

Recorded evaluation configuration: {"SSL":true,"LB":false,"PB":true}. This record does not assert independent reproduction.

### FixMatch + BOSS

Accuracy: 66.4. Result ID: 698f342f3a6c314849f6f9d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69301e209131cea20aea.md>)

[Implementation](<https://github.com/lnsmith54/BOSS>)

Recorded evaluation configuration: {"SSL":true,"LB":false,"PB":true}. This record does not assert independent reproduction.

### FixMatch + Logit Adjustment (LA)

Accuracy: 63.4. Result ID: 698f342f3a6c314849f6f9d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.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: {"SSL":true,"LB":true,"PB":false}. This record does not assert independent reproduction.

### FixMatch + CReST

Accuracy: 61.7. Result ID: 698f342f3a6c314849f6f9d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea26638.md>)

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

Recorded evaluation configuration: {"SSL":true,"LB":false,"PB":true}. This record does not assert independent reproduction.

### FixMatch + CReST+

Accuracy: 61.2. Result ID: 698f342f3a6c314849f6f9d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea26638.md>)

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

Recorded evaluation configuration: {"SSL":true,"LB":false,"PB":true}. This record does not assert independent reproduction.

### FixMatch + CB re-weight

Accuracy: 58.9. Result ID: 698f342f3a6c314849f6f9d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

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

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

Recorded evaluation configuration: {"SSL":true,"LB":true,"PB":false}. This record does not assert independent reproduction.

### FixMatch

Accuracy: 56.1. Result ID: 698f342f3a6c314849f6f9d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68d61e209131cea1e896.md>)

Recorded evaluation configuration: {"SSL":true,"LB":false,"PB":false}. This record does not assert independent reproduction.

### Logit Adjustment (LA)

Accuracy: 42.8. Result ID: 698f342f3a6c314849f6f9ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.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: {"SSL":false,"LB":true,"PB":false}. This record does not assert independent reproduction.

### PseudoLabel

Accuracy: 42.3. Result ID: 698f342f3a6c314849f6f9cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

Recorded evaluation configuration: {"SSL":true,"LB":false,"PB":false}. This record does not assert independent reproduction.

### LDAM-DRW

Accuracy: 41.8. Result ID: 698f342f3a6c314849f6f9cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

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

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

Recorded evaluation configuration: {"SSL":false,"LB":true,"PB":false}. This record does not assert independent reproduction.

### cRT

Accuracy: 40.8. Result ID: 698f342f3a6c314849f6f9cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa671b1e209131cea144a9.md>)

[Implementation](<https://github.com/facebookresearch/classifier-balancing>)

Recorded evaluation configuration: {"SSL":false,"LB":true,"PB":false}. This record does not assert independent reproduction.

### Supervised

Accuracy: 40.2. Result ID: 698f342f3a6c314849f6f9cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb71e209131cea3583a.md>)

Recorded evaluation configuration: {"SSL":false,"LB":false,"PB":false}. This record does not assert independent reproduction.

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