# Image Classification on ImageNet (Base, Novel, and HM Metrics)

Source: [Image Classification on ImageNet (Base, Novel, and HM Metrics)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-base-novel-and-hm-metrics>)

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

Data updated: 2026-02-26T05:37:38.064Z

Evaluation of Image Classification performance on the standard ImageNet dataset, measured using Base, Novel, and Harmonic Mean (HM) metrics.

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 | Classification |
| Dataset (including any stated split) | ImageNet |
| Metric | Base Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Base Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-base-novel-and-hm-metrics.md?metric=Base%20Accuracy>): Higher is better; unit: PERCENT.

- [Novel Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-base-novel-and-hm-metrics.md?metric=Novel%20Accuracy>): Higher is better; unit: PERCENT.

- [Harmonic Mean (HM)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-base-novel-and-hm-metrics.md?metric=Harmonic%20Mean%20(HM)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Base Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MMA | 83.17 | Not recorded | 68fa777a1e209131cea736e6 |
| 2SFS | 83.11 | Not recorded | 68fa777a1e209131cea736e6 |
| CLIP | 79.18 | Not recorded | 68fa777a1e209131cea736e6 |

### MMA

Base Accuracy: 83.17. Result ID: 6995377d3badfaffe61e3350.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea736e6.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Shots":16}. This record does not assert independent reproduction.

### 2SFS

Base Accuracy: 83.11. Result ID: 6995377d3badfaffe61e3351.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea736e6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea736e6.md>)

[Implementation](<https://github.com/FarinaMatteo/rethinking_fewshot_vlms>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Shots":16}. This record does not assert independent reproduction.

### CLIP

Base Accuracy: 79.18. Result ID: 6995377d3badfaffe61e334f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea736e6.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14","Shots":"Zero-shot"}. This record does not assert independent reproduction.

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