# Image Classification on Tiny ImageNet (test) with Model Efficiency Metrics

Source: [Image Classification on Tiny ImageNet (test) with Model Efficiency Metrics](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-test-with-model-efficiency-metrics>)

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

Data updated: 2026-03-18T08:38:29.287Z

Evaluation of Image Classification performance on the test split of the TinyImageNet dataset, reporting standard accuracy alongside model compression metrics such as parameter and FLOPs reduction.

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) | Tiny ImageNet (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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-tiny-imagenet-test-with-model-efficiency-metrics.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Parameter Reduction (%)](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-test-with-model-efficiency-metrics.md?metric=Parameter%20Reduction%20(%25)>): Higher is better; unit: PERCENT.

- [FLOPs Reduction (%)](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-test-with-model-efficiency-metrics.md?metric=FLOPs%20Reduction%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Pruned MLP | 4.28 | Not recorded | 69ba31870636e5bf4afc07a6 |
| Baseline MLP | 3.24 | Not recorded | 69ba31870636e5bf4afc07a6 |
| DynamicMLP | 2.97 | Not recorded | 69ba31870636e5bf4afc07a6 |
| Dropout MLP | 2.51 | Not recorded | 69ba31870636e5bf4afc07a6 |

### Pruned MLP

Accuracy: 4.28. Result ID: 69ba646747f34ce924a45235.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07a6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa624a1e209131ce9f8a38.md>)

Recorded evaluation configuration: {"Params":"3,197,384","FLOPs":"4,506,418"}. This record does not assert independent reproduction.

### Baseline MLP

Accuracy: 3.24. Result ID: 69ba646747f34ce924a45233.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07a6.md>)

Recorded evaluation configuration: {"Params":"3,197,384","FLOPs":"6,393,856"}. This record does not assert independent reproduction.

### DynamicMLP

Accuracy: 2.97. Result ID: 69ba646747f34ce924a45236.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07a6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07a6.md>)

Recorded evaluation configuration: {"Params":"3,197,640","FLOPs":"1,273,117"}. This record does not assert independent reproduction.

### Dropout MLP

Accuracy: 2.51. Result ID: 69ba646747f34ce924a45234.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31870636e5bf4afc07a6.md>)

Recorded evaluation configuration: {"Params":"3,197,384","FLOPs":"6,393,856"}. This record does not assert independent reproduction.

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