# Image Classification on Mini-ImageNet Transfer from DomainNet-Real (val)

Source: [Image Classification on Mini-ImageNet Transfer from DomainNet-Real (val)](<https://www.sota2.com/research/sota/image-classification-on-mini-imagenet-transfer-from-domainnet-real-val>)

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

Data updated: 2026-02-26T05:28:22.315Z

Evaluation of Image Classification performance on the validation split of Mini-ImageNet, specifically configured via transfer learning from the Real domain subset of DomainNet. Metrics include final accuracy and convergence steps.

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) | Mini-ImageNet Transfer from DomainNet-Real (val) |
| Metric | 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mini-imagenet-transfer-from-domainnet-real-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Convergence Step](<https://www.sota2.com/research/sota/image-classification-on-mini-imagenet-transfer-from-domainnet-real-val.md?metric=Convergence%20Step>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SimPLE | 59.92 | Not recorded | 68fa6ce71e209131cea36a79 |
| SimPLE | 58.73 | Not recorded | 68fa6ce71e209131cea36a79 |
| MixMatch Enhanced | 55.75 | Not recorded | 68fa6ce71e209131cea36a79 |
| MixMatch | 53.39 | Not recorded | 68fa6ce71e209131cea36a79 |
| MixMatch Enhanced | 52.83 | Not recorded | 68fa6ce71e209131cea36a79 |
| MixMatch | 50.31 | Not recorded | 68fa6ce71e209131cea36a79 |
| Supervised w/ EMA | 48.83 | Not recorded | 68fa6ce71e209131cea36a79 |

### SimPLE

Accuracy: 59.92. Result ID: 698f4bdf3a6c314849f7be8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

[Implementation](<https://www.sota2.com/github.com/zijian-hu/SimPLE>)

Recorded evaluation configuration: {"Backbone":"WRN 28-2","Number of labels":"4000","Initialization":"from scratch"}. This record does not assert independent reproduction.

### SimPLE

Accuracy: 58.73. Result ID: 698f4bdf3a6c314849f7be8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

[Implementation](<https://www.sota2.com/github.com/zijian-hu/SimPLE>)

Recorded evaluation configuration: {"Backbone":"WRN 28-2","Number of labels":"4000","Initialization":"Pre-trained (DomainNet-Real)"}. This record does not assert independent reproduction.

### MixMatch Enhanced

Accuracy: 55.75. Result ID: 698f4bdf3a6c314849f7be8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

Recorded evaluation configuration: {"Backbone":"WRN 28-2","Number of labels":"4000","Initialization":"Pre-trained (DomainNet-Real)"}. This record does not assert independent reproduction.

### MixMatch

Accuracy: 53.39. Result ID: 698f4bdf3a6c314849f7be88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66961e209131cea11261.md>)

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

Recorded evaluation configuration: {"Backbone":"WRN 28-2","Number of labels":"4000","Initialization":"Pre-trained (DomainNet-Real)"}. This record does not assert independent reproduction.

### MixMatch Enhanced

Accuracy: 52.83. Result ID: 698f4bdf3a6c314849f7be89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

Recorded evaluation configuration: {"Backbone":"WRN 28-2","Number of labels":"4000","Initialization":"from scratch"}. This record does not assert independent reproduction.

### MixMatch

Accuracy: 50.31. Result ID: 698f4bdf3a6c314849f7be87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66961e209131cea11261.md>)

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

Recorded evaluation configuration: {"Backbone":"WRN 28-2","Number of labels":"4000","Initialization":"from scratch"}. This record does not assert independent reproduction.

### Supervised w/ EMA

Accuracy: 48.83. Result ID: 698f4bdf3a6c314849f7be86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ce71e209131cea36a79.md>)

Recorded evaluation configuration: {"Backbone":"WRN 28-2","Number of labels":"4000","Initialization":"Labeled training set only"}. This record does not assert independent reproduction.

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