# Image Classification on TinyImageNet (NID Metrics)

Source: [Image Classification on TinyImageNet (NID Metrics)](<https://www.sota2.com/research/sota/image-classification-on-tinyimagenet-nid-metrics>)

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

Data updated: 2026-03-23T10:34:07.338Z

Evaluation of Image Classification performance on the TinyImageNet dataset, measured using specialized accuracy metrics derived from NID analysis (NID1\_0.05, NID1\_0.2, NID2).

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) | TinyImageNet |
| Metric | Top-1 Accuracy (NID1\_0.05) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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 (NID1\_0.05)](<https://www.sota2.com/research/sota/image-classification-on-tinyimagenet-nid-metrics.md?metric=Top-1%20Accuracy%20(NID1_0.05)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (NID1\_0.2)](<https://www.sota2.com/research/sota/image-classification-on-tinyimagenet-nid-metrics.md?metric=Top-1%20Accuracy%20(NID1_0.2)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (NID2)](<https://www.sota2.com/research/sota/image-classification-on-tinyimagenet-nid-metrics.md?metric=Top-1%20Accuracy%20(NID2)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (NID1\_0.05) | Result date | Report paper |
| --- | --- | --- | --- |
| SemanticFL | 43.25 | Not recorded | 69c0c9040636e5bf4afc3b82 |
| FedDifRC | 42.63 | Not recorded | 69c0c9040636e5bf4afc3b82 |
| FedRCL | 41.33 | Not recorded | 69c0c9040636e5bf4afc3b82 |
| FedCDA | 41.18 | Not recorded | 69c0c9040636e5bf4afc3b82 |
| FedDisco | 40.83 | Not recorded | 69c0c9040636e5bf4afc3b82 |
| MOON | 40.79 | Not recorded | 69c0c9040636e5bf4afc3b82 |
| FedAvg | 40.41 | Not recorded | 69c0c9040636e5bf4afc3b82 |
| FedProx | 40.2 | Not recorded | 69c0c9040636e5bf4afc3b82 |

### SemanticFL

Top-1 Accuracy (NID1\_0.05): 43.25. Result ID: 69c1152747f34ce924a92923.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FedDifRC

Top-1 Accuracy (NID1\_0.05): 42.63. Result ID: 69c1152747f34ce924a92922.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a171e209131cea811a0.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FedRCL

Top-1 Accuracy (NID1\_0.05): 41.33. Result ID: 69c1152747f34ce924a92921.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73611e209131cea5c107.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FedCDA

Top-1 Accuracy (NID1\_0.05): 41.18. Result ID: 69c1152747f34ce924a92920.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FedDisco

Top-1 Accuracy (NID1\_0.05): 40.83. Result ID: 69c1152747f34ce924a9291f.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f951e209131cea4671a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MOON

Top-1 Accuracy (NID1\_0.05): 40.79. Result ID: 69c1152747f34ce924a9291e.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa699a1e209131cea22fca.md>)

[Implementation](<https://github.com/QinbinLi/MOON>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FedAvg

Top-1 Accuracy (NID1\_0.05): 40.41. Result ID: 69c1152747f34ce924a9291c.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FedProx

Top-1 Accuracy (NID1\_0.05): 40.2. Result ID: 69c1152747f34ce924a9291d.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c9040636e5bf4afc3b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67701e209131cea163fe.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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