# Image Classification on CIFAR-10 (test) (Delay and Overhead Gain)

Source: [Image Classification on CIFAR-10 (test) (Delay and Overhead Gain)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-delay-and-overhead-gain>)

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

Data updated: 2026-03-10T13:39:14.054Z

Evaluation of Image Classification performance on the CIFAR-10 test set, specifically reporting metrics related to model latency and operational overhead gains.

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) | CIFAR-10 (test) |
| Metric | Delay Gain (%) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Delay Gain (%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-delay-and-overhead-gain.md?metric=Delay%20Gain%20(%25)>): Higher is better; unit: PERCENT.

- [Overhead Gain (%)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-delay-and-overhead-gain.md?metric=Overhead%20Gain%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Delay Gain (%) | Result date | Report paper |
| --- | --- | --- | --- |
| AA HSFL-ll | 35 | Not recorded | 69afa5b12d603e6de3e43dd1 |
| AA HSFL-ll | 28.41 | Not recorded | 69afa5b12d603e6de3e43dd1 |
| AA HSFL-ll | 11.34 | Not recorded | 69afa5b12d603e6de3e43dd1 |
| AA HSFL-ll | 11 | Not recorded | 69afa5b12d603e6de3e43dd1 |
| AA HSFL-ll | 8.22 | Not recorded | 69afa5b12d603e6de3e43dd1 |
| AA HSFL-ll | 5.48 | Not recorded | 69afa5b12d603e6de3e43dd1 |

### AA HSFL-ll

Delay Gain (%): 35. Result ID: 69b01eea6dbb7075b95a46b8.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

Recorded evaluation configuration: {"Model":"VGG-11","Acc. Target(%)":"65"}. This record does not assert independent reproduction.

### AA HSFL-ll

Delay Gain (%): 28.41. Result ID: 69b01eea6dbb7075b95a46b9.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

Recorded evaluation configuration: {"Model":"VGG-11","Acc. Target(%)":"70"}. This record does not assert independent reproduction.

### AA HSFL-ll

Delay Gain (%): 11.34. Result ID: 69b01eea6dbb7075b95a46ba.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

Recorded evaluation configuration: {"Model":"VGG-11","Acc. Target(%)":"75"}. This record does not assert independent reproduction.

### AA HSFL-ll

Delay Gain (%): 11. Result ID: 69b01eea6dbb7075b95a46bc.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

Recorded evaluation configuration: {"Model":"VGG-19","Acc. Target(%)":"85"}. This record does not assert independent reproduction.

### AA HSFL-ll

Delay Gain (%): 8.22. Result ID: 69b01eea6dbb7075b95a46bd.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

Recorded evaluation configuration: {"Model":"VGG-19","Acc. Target(%)":"90"}. This record does not assert independent reproduction.

### AA HSFL-ll

Delay Gain (%): 5.48. Result ID: 69b01eea6dbb7075b95a46bb.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5b12d603e6de3e43dd1.md>)

Recorded evaluation configuration: {"Model":"VGG-19","Acc. Target(%)":"80"}. This record does not assert independent reproduction.

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