# Image Classification on ImageNet-1K (test) (Epoch-Specific Top-1 Accuracy)

Source: [Image Classification on ImageNet-1K (test) (Epoch-Specific Top-1 Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-test-epoch-specific-top-1-accuracy>)

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

Data updated: 2026-06-02T12:43:57.369Z

Evaluation of Image Classification performance on the test split of ImageNet-1K, reporting Top-1 Accuracy measured after 20, 40, and 60 training epochs.

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) | ImageNet-1K (test) |
| Metric | Top-1 Accuracy (@20 epoch) |
| 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

- [Top-1 Accuracy (@20 epoch)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-test-epoch-specific-top-1-accuracy.md?metric=Top-1%20Accuracy%20(%4020%20epoch)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (@40 epoch)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-test-epoch-specific-top-1-accuracy.md?metric=Top-1%20Accuracy%20(%4040%20epoch)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (@60 epoch)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-test-epoch-specific-top-1-accuracy.md?metric=Top-1%20Accuracy%20(%4060%20epoch)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (@20 epoch) | Result date | Report paper |
| --- | --- | --- | --- |
| AdamW | 67.8 | Not recorded | 6a1e6447dbd7150506f85967 |
| LPSGDM | 66.26 | Not recorded | 6a1e6447dbd7150506f85967 |
| Lion | 65.23 | Not recorded | 6a1e6447dbd7150506f85967 |
| SGD w/ Momentum | 52.19 | Not recorded | 6a1e6447dbd7150506f85967 |

### AdamW

Top-1 Accuracy (@20 epoch): 67.8. Result ID: 6a1ecff7fbc373592c1a9619.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa55761e209131ce9946db.md>)

Recorded evaluation configuration: {"Model":"ResNet-50","Optimizer":"AdamW"}. This record does not assert independent reproduction.

### LPSGDM

Top-1 Accuracy (@20 epoch): 66.26. Result ID: 6a1ecff7fbc373592c1a961b.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

Recorded evaluation configuration: {"Model":"ResNet-50","Optimizer":"LPSGDM"}. This record does not assert independent reproduction.

### Lion

Top-1 Accuracy (@20 epoch): 65.23. Result ID: 6a1ecff7fbc373592c1a961a.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f421e209131cea448e3.md>)

[Implementation](<https://github.com/google/automl/tree/master/lion>)

Recorded evaluation configuration: {"Model":"ResNet-50","Optimizer":"Lion"}. This record does not assert independent reproduction.

### SGD w/ Momentum

Top-1 Accuracy (@20 epoch): 52.19. Result ID: 6a1ecff7fbc373592c1a9618.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e6447dbd7150506f85967.md>)

Recorded evaluation configuration: {"Model":"ResNet-50","Optimizer":"SGD w/ Momentum"}. This record does not assert independent reproduction.

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