# Image Classification on CIFAR-10 (Accuracy, Parameter Reduction)

Source: [Image Classification on CIFAR-10 (Accuracy, Parameter Reduction)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-parameter-reduction>)

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

Data updated: 2026-04-08T09:02:11.543Z

Evaluation of Image Classification performance on the CIFAR-10 dataset, reporting standard accuracy alongside model parameter reduction efficiency.

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 |
| Metric | 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-parameter-reduction.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Parameter Reduction Factor](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-accuracy-parameter-reduction.md?metric=Parameter%20Reduction%20Factor>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| LoRA | 97.92 | Not recorded | 69d5e10b7d0172140ec75aaa |
| CDWF | 96.81 | Not recorded | 69d5e10b7d0172140ec75aaa |
| Full Fine-tuning (FL) | 96.33 | Not recorded | 69d5e10b7d0172140ec75aaa |
| Full Fine-tuning (FL) | 86.94 | Not recorded | 69d5e10b7d0172140ec75aaa |
| Full Fine-tuning (FL) | 85.63 | Not recorded | 69d5e10b7d0172140ec75aaa |
| CDWF | 84.79 | Not recorded | 69d5e10b7d0172140ec75aaa |
| CDWF | 83.19 | Not recorded | 69d5e10b7d0172140ec75aaa |
| LoRA | 81.74 | Not recorded | 69d5e10b7d0172140ec75aaa |
| LoRA | 77.43 | Not recorded | 69d5e10b7d0172140ec75aaa |

### LoRA

Accuracy: 97.92. Result ID: 69d6198247f34ce924bed639.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### CDWF

Accuracy: 96.81. Result ID: 69d6198247f34ce924bed63c.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Parameter Budget (fmax)":"0.05"}. This record does not assert independent reproduction.

### Full Fine-tuning (FL)

Accuracy: 96.33. Result ID: 69d6198247f34ce924bed636.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea04261.md>)

[Implementation](<http://nlp.fast.ai/ulmfit>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16"}. This record does not assert independent reproduction.

### Full Fine-tuning (FL)

Accuracy: 86.94. Result ID: 69d6198247f34ce924bed635.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea04261.md>)

[Implementation](<http://nlp.fast.ai/ulmfit>)

Recorded evaluation configuration: {"Backbone":"ResNet-101"}. This record does not assert independent reproduction.

### Full Fine-tuning (FL)

Accuracy: 85.63. Result ID: 69d6198247f34ce924bed634.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64601e209131cea04261.md>)

[Implementation](<http://nlp.fast.ai/ulmfit>)

Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### CDWF

Accuracy: 84.79. Result ID: 69d6198247f34ce924bed63b.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-101","Parameter Budget (fmax)":"0.05"}. This record does not assert independent reproduction.

### CDWF

Accuracy: 83.19. Result ID: 69d6198247f34ce924bed63a.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Parameter Budget (fmax)":"0.05"}. This record does not assert independent reproduction.

### LoRA

Accuracy: 81.74. Result ID: 69d6198247f34ce924bed638.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Backbone":"ResNet-101"}. This record does not assert independent reproduction.

### LoRA

Accuracy: 77.43. Result ID: 69d6198247f34ce924bed637.

[Reporting paper](<https://www.sota2.com/research/paper/69d5e10b7d0172140ec75aaa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction.

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