# Image Classification on ImageNet Rendition (novel classes)

Source: [Image Classification on ImageNet Rendition (novel classes)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-rendition-novel-classes>)

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

Data updated: 2026-02-27T14:19:32.327Z

Evaluation of Image Classification performance on the novel classes subset of the ImageNet Rendition dataset, reporting Accuracy and Expected Calibration Error (ECE).

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) | ImageNet Rendition (novel classes) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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-imagenet-rendition-novel-classes.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Expected Calibration Error (ECE)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-rendition-novel-classes.md?metric=Expected%20Calibration%20Error%20(ECE)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TCPT | 85.28 | Not recorded | 699d30716017c4460ffab2ff |
| MaPLe | 85.22 | Not recorded | 699d30716017c4460ffab2ff |
| ZS-Norm | 85.16 | Not recorded | 699d30716017c4460ffab2ff |
| Penalty | 85.16 | Not recorded | 699d30716017c4460ffab2ff |

### TCPT

Accuracy: 85.28. Result ID: 69a1a7d535dfcabb00e7ffee.

[Reporting paper](<https://www.sota2.com/research/paper/699d30716017c4460ffab2ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30716017c4460ffab2ff.md>)

Recorded evaluation configuration: {"Prompting Method":"MaPLe"}. This record does not assert independent reproduction.

### MaPLe

Accuracy: 85.22. Result ID: 69a1a7d535dfcabb00e7ffeb.

[Reporting paper](<https://www.sota2.com/research/paper/699d30716017c4460ffab2ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef21e209131cea4311c.md>)

[Implementation](<https://github.com/muzairkhattak/multimodal-prompt-learning>)

Recorded evaluation configuration: {"Method":"Prompt-tuning"}. This record does not assert independent reproduction.

### ZS-Norm

Accuracy: 85.16. Result ID: 69a1a7d535dfcabb00e7ffec.

[Reporting paper](<https://www.sota2.com/research/paper/699d30716017c4460ffab2ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74301e209131cea60514.md>)

Recorded evaluation configuration: {"Prompting Method":"MaPLe"}. This record does not assert independent reproduction.

### Penalty

Accuracy: 85.16. Result ID: 69a1a7d535dfcabb00e7ffed.

[Reporting paper](<https://www.sota2.com/research/paper/699d30716017c4460ffab2ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74301e209131cea60514.md>)

Recorded evaluation configuration: {"Prompting Method":"MaPLe"}. This record does not assert independent reproduction.

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