# Medical Image Classification on ChestMNIST (Including Resource Metrics)

Source: [Medical Image Classification on ChestMNIST (Including Resource Metrics)](<https://www.sota2.com/research/sota/medical-image-classification-on-chestmnist-including-resource-metrics>)

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

Data updated: 2026-05-08T08:07:25.621Z

Evaluation of Medical Image Classification performance on the ChestMNIST dataset, reporting standard metrics (Accuracy, AUC) alongside resource consumption (Memory) and delta metrics.

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 | Medical Image Classification |
| Dataset (including any stated split) | ChestMNIST |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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/medical-image-classification-on-chestmnist-including-resource-metrics.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/medical-image-classification-on-chestmnist-including-resource-metrics.md?metric=AUC>): Higher is better; unit: PERCENT.

- [Memory (GB)](<https://www.sota2.com/research/sota/medical-image-classification-on-chestmnist-including-resource-metrics.md?metric=Memory%20(GB)>): Lower is better; unit: SIZE.

- [Delta Accuracy (ΔAcc)](<https://www.sota2.com/research/sota/medical-image-classification-on-chestmnist-including-resource-metrics.md?metric=Delta%20Accuracy%20(%CE%94Acc)>): Higher is better; unit: PERCENT.

- [Delta AUC (ΔAUC)](<https://www.sota2.com/research/sota/medical-image-classification-on-chestmnist-including-resource-metrics.md?metric=Delta%20AUC%20(%CE%94AUC)>): Higher is better; unit: PERCENT.

- [MF/BP Memory](<https://www.sota2.com/research/sota/medical-image-classification-on-chestmnist-including-resource-metrics.md?metric=MF%2FBP%20Memory>): Lower is better; unit: SIZE.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MLP-Mixer (Back-Propagation) | 94.76 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Mono-Forward) | 94.76 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Back-Propagation) | 94.76 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Back-Propagation) | 94.76 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Back-Propagation) | 94.76 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Mono-Forward) | 94.75 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Mono-Forward) | 94.75 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Mono-Forward) | 94.75 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Back-Propagation) | 94.75 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Mono-Forward) | 94.75 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Back-Propagation) | 94.75 | Not recorded | 68fa769d1e209131cea6e24f |
| MLP-Mixer (Mono-Forward) | 94.75 | Not recorded | 68fa769d1e209131cea6e24f |

### MLP-Mixer (Back-Propagation)

Accuracy: 94.76. Result ID: 69fd99b447f34ce924e0759a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

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

Recorded evaluation configuration: {"Arch":"D5-W256","Training Protocol":"BP"}. This record does not assert independent reproduction.

### MLP-Mixer (Mono-Forward)

Accuracy: 94.76. Result ID: 69fd99b447f34ce924e0759b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

Recorded evaluation configuration: {"Arch":"D5-W256","Training Protocol":"MF"}. This record does not assert independent reproduction.

### MLP-Mixer (Back-Propagation)

Accuracy: 94.76. Result ID: 69fd99b447f34ce924e0759c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

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

Recorded evaluation configuration: {"Arch":"D5-W512","Training Protocol":"BP"}. This record does not assert independent reproduction.

### MLP-Mixer (Back-Propagation)

Accuracy: 94.76. Result ID: 69fd99b447f34ce924e0759e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

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

Recorded evaluation configuration: {"Arch":"D8-W256","Training Protocol":"BP"}. This record does not assert independent reproduction.

### MLP-Mixer (Back-Propagation)

Accuracy: 94.76. Result ID: 69fd99b447f34ce924e075a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

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

Recorded evaluation configuration: {"Arch":"D8-W512","Training Protocol":"BP"}. This record does not assert independent reproduction.

### MLP-Mixer (Mono-Forward)

Accuracy: 94.75. Result ID: 69fd99b447f34ce924e0759d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

Recorded evaluation configuration: {"Arch":"D5-W512","Training Protocol":"MF"}. This record does not assert independent reproduction.

### MLP-Mixer (Mono-Forward)

Accuracy: 94.75. Result ID: 69fd99b447f34ce924e0759f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

Recorded evaluation configuration: {"Arch":"D8-W256","Training Protocol":"MF"}. This record does not assert independent reproduction.

### MLP-Mixer (Mono-Forward)

Accuracy: 94.75. Result ID: 69fd99b447f34ce924e075a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

Recorded evaluation configuration: {"Arch":"D8-W512","Training Protocol":"MF"}. This record does not assert independent reproduction.

### MLP-Mixer (Back-Propagation)

Accuracy: 94.75. Result ID: 69fd99b447f34ce924e075a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

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

Recorded evaluation configuration: {"Arch":"D12-W256","Training Protocol":"BP"}. This record does not assert independent reproduction.

### MLP-Mixer (Mono-Forward)

Accuracy: 94.75. Result ID: 69fd99b447f34ce924e075a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

Recorded evaluation configuration: {"Arch":"D12-W256","Training Protocol":"MF"}. This record does not assert independent reproduction.

### MLP-Mixer (Back-Propagation)

Accuracy: 94.75. Result ID: 69fd99b447f34ce924e075a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a201e209131cea26207.md>)

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

Recorded evaluation configuration: {"Arch":"D12-W512","Training Protocol":"BP"}. This record does not assert independent reproduction.

### MLP-Mixer (Mono-Forward)

Accuracy: 94.75. Result ID: 69fd99b447f34ce924e075a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769d1e209131cea6e24f.md>)

Recorded evaluation configuration: {"Arch":"D12-W512","Training Protocol":"MF"}. This record does not assert independent reproduction.

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