# Image Classification on ImageNet-100 (retrain)

Source: [Image Classification on ImageNet-100 (retrain)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-retrain>)

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

Data updated: 2026-02-26T06:07:03.092Z

Evaluation of Image Classification performance on the retrained version of the ImageNet-100 dataset, typically measured by Top-1 Accuracy.

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-100 (retrain) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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-100-retrain.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Supernet Shifting | 85.61 | Not recorded | 68fa72971e209131cea575fe |
| SPOS (block) | 85.5 | Not recorded | 68fa72971e209131cea575fe |
| FairNAS | 85.44 | Not recorded | 68fa72971e209131cea575fe |
| Random select | 85.42 | Not recorded | 68fa72971e209131cea575fe |
| Oneshot | 85.41 | Not recorded | 68fa72971e209131cea575fe |

### Supernet Shifting

Top-1 Accuracy: 85.61. Result ID: 6992453c3a6c3148490dcaa1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72971e209131cea575fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72971e209131cea575fe.md>)

[Implementation](<https://github.com/beichenzbc/Supernet-shifting>)

Recorded evaluation configuration: {"Flops":"299M","Search Space":"ShuffleNet-V2"}. This record does not assert independent reproduction.

### SPOS (block)

Top-1 Accuracy: 85.5. Result ID: 6992453c3a6c3148490dca9f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72971e209131cea575fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ed1e209131cea19308.md>)

Recorded evaluation configuration: {"Flops":"304M","Search Space":"ShuffleNet-V2"}. This record does not assert independent reproduction.

### FairNAS

Top-1 Accuracy: 85.44. Result ID: 6992453c3a6c3148490dcaa0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72971e209131cea575fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a6e1e209131cea27fd7.md>)

Recorded evaluation configuration: {"Flops":"300M","Search Space":"ShuffleNet-V2"}. This record does not assert independent reproduction.

### Random select

Top-1 Accuracy: 85.42. Result ID: 6992453c3a6c3148490dca9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72971e209131cea575fe.md>)

Recorded evaluation configuration: {"Flops":"312M","Search Space":"ShuffleNet-V2"}. This record does not assert independent reproduction.

### Oneshot

Top-1 Accuracy: 85.41. Result ID: 6992453c3a6c3148490dca9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72971e209131cea575fe.md>)

Recorded evaluation configuration: {"Flops":"304M","Search Space":"ShuffleNet-V2"}. This record does not assert independent reproduction.

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