# Image Classification on CIFAR-100-LT (Uniform split)

Source: [Image Classification on CIFAR-100-LT (Uniform split)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-lt-uniform-split>)

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

Data updated: 2026-05-19T08:04:22.537Z

Evaluation of Image Classification performance on the CIFAR-100 Long Tail (LT) dataset using the Uniform split configuration, measured by 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) | CIFAR-100-LT (Uniform split) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-lt-uniform-split.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FixMatch + AdaptFormer + DECON | 83.6 | Not recorded | 68fa73bd1e209131cea5e2e5 |
| FixMatch + AdaptFormer + ACR | 83.3 | Not recorded | 68fa73bd1e209131cea5e2e5 |
| FixMatch + VPT + DECON | 82.9 | Not recorded | 68fa73bd1e209131cea5e2e5 |
| FixMatch + AdaptFormer | 81.7 | Not recorded | 68fa73bd1e209131cea5e2e5 |
| FixMatch + VPT | 81.3 | Not recorded | 68fa73bd1e209131cea5e2e5 |
| FixMatch + VPT + ACR | 81.2 | Not recorded | 68fa73bd1e209131cea5e2e5 |

### FixMatch + AdaptFormer + DECON

Accuracy: 83.6. Result ID: 6a0c1984fbc373592c0207fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e5.md>)

Recorded evaluation configuration: {"Fine-tuning strategy":"AdaptFormer","Pre-trained model":"CLIP"}. This record does not assert independent reproduction.

### FixMatch + AdaptFormer + ACR

Accuracy: 83.3. Result ID: 6a0c1984fbc373592c0207f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e5.md>)

Recorded evaluation configuration: {"Fine-tuning strategy":"AdaptFormer","Pre-trained model":"CLIP"}. This record does not assert independent reproduction.

### FixMatch + VPT + DECON

Accuracy: 82.9. Result ID: 6a0c1984fbc373592c0207f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e5.md>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Visual Prompt Tuning (VPT)","Pre-trained model":"CLIP"}. This record does not assert independent reproduction.

### FixMatch + AdaptFormer

Accuracy: 81.7. Result ID: 6a0c1984fbc373592c0207f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dab1e209131cea3b5b4.md>)

[Implementation](<https://github.com/ShoufaChen/AdaptFormer>)

Recorded evaluation configuration: {"Fine-tuning strategy":"AdaptFormer","Pre-trained model":"CLIP"}. This record does not assert independent reproduction.

### FixMatch + VPT

Accuracy: 81.3. Result ID: 6a0c1984fbc373592c0207f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d181e209131cea37ae9.md>)

[Implementation](<https://www.sota2.com/github.com/kmnp/vpt>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Visual Prompt Tuning (VPT)","Pre-trained model":"CLIP"}. This record does not assert independent reproduction.

### FixMatch + VPT + ACR

Accuracy: 81.2. Result ID: 6a0c1984fbc373592c0207f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73bd1e209131cea5e2e5.md>)

Recorded evaluation configuration: {"Fine-tuning strategy":"Visual Prompt Tuning (VPT)","Pre-trained model":"CLIP"}. This record does not assert independent reproduction.

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