# Image Classification on ImageNet-1K 1.0 (val) (Top-1 Acc and Training Efficiency)

Source: [Image Classification on ImageNet-1K 1.0 (val) (Top-1 Acc and Training Efficiency)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-1-0-val-top-1-acc-and-training-efficiency>)

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

Data updated: 2026-02-26T06:07:03.371Z

Standard evaluation of Image Classification performance on the ImageNet-1K validation set (v1.0), reporting Top-1 Accuracy alongside training efficiency metrics such as GFLOPS per iteration and total training time.

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 1.0 (val) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-1-0-val-top-1-acc-and-training-efficiency.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [GFLOPS per Iteration](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-1-0-val-top-1-acc-and-training-efficiency.md?metric=GFLOPS%20per%20Iteration>): Lower is better; unit: SCALAR.

- [Total Training Time (GPU Hours)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-1-0-val-top-1-acc-and-training-efficiency.md?metric=Total%20Training%20Time%20(GPU%20Hours)>): Lower is better; unit: TIME.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Baseline | 84.1 | Not recorded | 68fa72be1e209131cea58525 |
| ToE | 84.1 | Not recorded | 68fa72be1e209131cea58525 |
| NetworkExpansion | 84 | Not recorded | 68fa72be1e209131cea58525 |
| Baseline | 83.3 | Not recorded | 68fa72be1e209131cea58525 |
| ToE | 83.3 | Not recorded | 68fa72be1e209131cea58525 |
| NetworkExpansion | 82.9 | Not recorded | 68fa72be1e209131cea58525 |
| ToE | 79.4 | Not recorded | 68fa72be1e209131cea58525 |
| Baseline | 79.1 | Not recorded | 68fa72be1e209131cea58525 |
| NetworkExpansion | 78.8 | Not recorded | 68fa72be1e209131cea58525 |

### Baseline

Top-1 Accuracy: 84.1. Result ID: 699276663a6c3148490f1f78.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1d1e209131cea25fd2.md>)

[Implementation](<https://github.com/zihangJiang/TokenLabeling>)

Recorded evaluation configuration: {"Model":"LV-ViT-M"}. This record does not assert independent reproduction.

### ToE

Top-1 Accuracy: 84.1. Result ID: 699276663a6c3148490f1f7a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Implementation](<https://github.com/Osilly/TokenExpansion>)

Recorded evaluation configuration: {"Model":"LV-ViT-M","r1":0.4}. This record does not assert independent reproduction.

### NetworkExpansion

Top-1 Accuracy: 84. Result ID: 699276663a6c3148490f1f79.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

Recorded evaluation configuration: {"Model":"LV-ViT-M","Expansion":"10 to 20"}. This record does not assert independent reproduction.

### Baseline

Top-1 Accuracy: 83.3. Result ID: 699276663a6c3148490f1f75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1d1e209131cea25fd2.md>)

[Implementation](<https://github.com/zihangJiang/TokenLabeling>)

Recorded evaluation configuration: {"Model":"LV-ViT-S"}. This record does not assert independent reproduction.

### ToE

Top-1 Accuracy: 83.3. Result ID: 699276663a6c3148490f1f77.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Implementation](<https://github.com/Osilly/TokenExpansion>)

Recorded evaluation configuration: {"Model":"LV-ViT-S","r1":0.4}. This record does not assert independent reproduction.

### NetworkExpansion

Top-1 Accuracy: 82.9. Result ID: 699276663a6c3148490f1f76.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

Recorded evaluation configuration: {"Model":"LV-ViT-S","Expansion":"8 to 16"}. This record does not assert independent reproduction.

### ToE

Top-1 Accuracy: 79.4. Result ID: 699276663a6c3148490f1f74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Implementation](<https://github.com/Osilly/TokenExpansion>)

Recorded evaluation configuration: {"Model":"LV-ViT-T","r1":0.4}. This record does not assert independent reproduction.

### Baseline

Top-1 Accuracy: 79.1. Result ID: 699276663a6c3148490f1f72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1d1e209131cea25fd2.md>)

[Implementation](<https://github.com/zihangJiang/TokenLabeling>)

Recorded evaluation configuration: {"Model":"LV-ViT-T"}. This record does not assert independent reproduction.

### NetworkExpansion

Top-1 Accuracy: 78.8. Result ID: 699276663a6c3148490f1f73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72be1e209131cea58525.md>)

Recorded evaluation configuration: {"Model":"LV-ViT-T","Expansion":"6 to 12"}. This record does not assert independent reproduction.

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