# Image Classification on CIFAR-100 (test) (Alpha Accuracy Profile)

Source: [Image Classification on CIFAR-100 (test) (Alpha Accuracy Profile)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-alpha-accuracy-profile>)

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

Data updated: 2026-04-20T08:17:20.661Z

Evaluation of Image Classification performance on the CIFAR-100 test set, reporting accuracy metrics calculated using specific alpha weighting factors (alpha=0.1, 0.5, 1.0).

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 (test) |
| Metric | Accuracy (alpha=0.1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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 (alpha=0.1)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-alpha-accuracy-profile.md?metric=Accuracy%20(alpha%3D0.1)>): Higher is better; unit: PERCENT.

- [Accuracy (alpha=0.5)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-alpha-accuracy-profile.md?metric=Accuracy%20(alpha%3D0.5)>): Higher is better; unit: PERCENT.

- [Accuracy (alpha=1.0)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-alpha-accuracy-profile.md?metric=Accuracy%20(alpha%3D1.0)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (alpha=0.1) | Result date | Report paper |
| --- | --- | --- | --- |
| FedTSP-CLIP-FT | 62.3 | Not recorded | 68fa77781e209131cea735c9 |
| FedTSP-BERT-FT | 61.05 | Not recorded | 68fa77781e209131cea735c9 |
| FedBABU-FT | 60.1 | Not recorded | 68fa77781e209131cea735c9 |
| FedAvg-FT | 60.08 | Not recorded | 68fa77781e209131cea735c9 |
| FedPAC | 58.19 | Not recorded | 68fa77781e209131cea735c9 |
| FedETF-Per | 57 | Not recorded | 68fa77781e209131cea735c9 |
| FedFA-FT | 42.62 | Not recorded | 68fa77781e209131cea735c9 |
| FedPCL | 42.61 | Not recorded | 68fa77781e209131cea735c9 |
| FedTSP-CLIP | 37.98 | Not recorded | 68fa77781e209131cea735c9 |
| FedTSP-BERT | 37.27 | Not recorded | 68fa77781e209131cea735c9 |
| FedBABU | 36.37 | Not recorded | 68fa77781e209131cea735c9 |
| FedFA | 35.16 | Not recorded | 68fa77781e209131cea735c9 |
| FedAvg | 34.47 | Not recorded | 68fa77781e209131cea735c9 |
| FedETF | 33.84 | Not recorded | 68fa77781e209131cea735c9 |

### FedTSP-CLIP-FT

Accuracy (alpha=0.1): 62.3. Result ID: 69e5e10c47f34ce924cbf7a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

Recorded evaluation configuration: {"Setting":"Personalized Federated Learning","Encoder":"CLIP","fine-tuning":"true"}. This record does not assert independent reproduction.

### FedTSP-BERT-FT

Accuracy (alpha=0.1): 61.05. Result ID: 69e5e10c47f34ce924cbf7a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

Recorded evaluation configuration: {"Setting":"Personalized Federated Learning","Encoder":"BERT","fine-tuning":"true"}. This record does not assert independent reproduction.

### FedBABU-FT

Accuracy (alpha=0.1): 60.1. Result ID: 69e5e10c47f34ce924cbf79e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfa1e209131cea31630.md>)

Recorded evaluation configuration: {"Setting":"Personalized Federated Learning","fine-tuning":"true"}. This record does not assert independent reproduction.

### FedAvg-FT

Accuracy (alpha=0.1): 60.08. Result ID: 69e5e10c47f34ce924cbf79d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e761e209131cea40072.md>)

Recorded evaluation configuration: {"Setting":"Personalized Federated Learning","fine-tuning":"true"}. This record does not assert independent reproduction.

### FedPAC

Accuracy (alpha=0.1): 58.19. Result ID: 69e5e10c47f34ce924cbf7a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea4759f.md>)

Recorded evaluation configuration: {"Setting":"Personalized Federated Learning"}. This record does not assert independent reproduction.

### FedETF-Per

Accuracy (alpha=0.1): 57. Result ID: 69e5e10c47f34ce924cbf79f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70731e209131cea4b1ab.md>)

Recorded evaluation configuration: {"Setting":"Personalized Federated Learning","personalization":"true"}. This record does not assert independent reproduction.

### FedFA-FT

Accuracy (alpha=0.1): 42.62. Result ID: 69e5e10c47f34ce924cbf7a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ef1e209131cea4e22f.md>)

Recorded evaluation configuration: {"Setting":"Personalized Federated Learning","fine-tuning":"true"}. This record does not assert independent reproduction.

### FedPCL

Accuracy (alpha=0.1): 42.61. Result ID: 69e5e10c47f34ce924cbf7a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703b1e209131cea49c52.md>)

Recorded evaluation configuration: {"Setting":"Personalized Federated Learning"}. This record does not assert independent reproduction.

### FedTSP-CLIP

Accuracy (alpha=0.1): 37.98. Result ID: 69e5e10c47f34ce924cbf79b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

Recorded evaluation configuration: {"Setting":"General Federated Learning","Encoder":"CLIP"}. This record does not assert independent reproduction.

### FedTSP-BERT

Accuracy (alpha=0.1): 37.27. Result ID: 69e5e10c47f34ce924cbf79c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

Recorded evaluation configuration: {"Setting":"General Federated Learning","Encoder":"BERT"}. This record does not assert independent reproduction.

### FedBABU

Accuracy (alpha=0.1): 36.37. Result ID: 69e5e10c47f34ce924cbf798.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfa1e209131cea31630.md>)

Recorded evaluation configuration: {"Setting":"General Federated Learning"}. This record does not assert independent reproduction.

### FedFA

Accuracy (alpha=0.1): 35.16. Result ID: 69e5e10c47f34ce924cbf79a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70ef1e209131cea4e22f.md>)

Recorded evaluation configuration: {"Setting":"General Federated Learning"}. This record does not assert independent reproduction.

### FedAvg

Accuracy (alpha=0.1): 34.47. Result ID: 69e5e10c47f34ce924cbf797.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e761e209131cea40072.md>)

Recorded evaluation configuration: {"Setting":"General Federated Learning"}. This record does not assert independent reproduction.

### FedETF

Accuracy (alpha=0.1): 33.84. Result ID: 69e5e10c47f34ce924cbf799.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77781e209131cea735c9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70731e209131cea4b1ab.md>)

Recorded evaluation configuration: {"Setting":"General Federated Learning"}. This record does not assert independent reproduction.

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