# Image Classification on ImageNet100 (long-tail)

Source: [Image Classification on ImageNet100 (long-tail)](<https://www.sota2.com/research/sota/image-classification-on-imagenet100-long-tail>)

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

Data updated: 2026-02-26T05:34:18.915Z

Evaluation of Image Classification performance specifically on the long-tail distribution subset of the ImageNet-100 dataset, measured by performance metrics on the long, tail, and average classes.

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) | ImageNet100 (long-tail) |
| Metric | Accuracy (Long) |
| 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 (Long)](<https://www.sota2.com/research/sota/image-classification-on-imagenet100-long-tail.md?metric=Accuracy%20(Long)>): Higher is better; unit: PERCENT.

- [Accuracy (Tail)](<https://www.sota2.com/research/sota/image-classification-on-imagenet100-long-tail.md?metric=Accuracy%20(Tail)>): Higher is better; unit: PERCENT.

- [Accuracy (Average)](<https://www.sota2.com/research/sota/image-classification-on-imagenet100-long-tail.md?metric=Accuracy%20(Average)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Long) | Result date | Report paper |
| --- | --- | --- | --- |
| LoFT | 88.9 | Not recorded | 699d30a56017c4460ffab593 |
| ChimeraLoRA | 88.8 | Not recorded | 699d30a56017c4460ffab593 |
| DataDream | 88.7 | Not recorded | 699d30a56017c4460ffab593 |
| Real | 78.8 | Not recorded | 699d30a56017c4460ffab593 |

### LoFT

Accuracy (Long): 88.9. Result ID: 699e53305698665ec412c006.

[Reporting paper](<https://www.sota2.com/research/paper/699d30a56017c4460ffab593.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78971e209131cea792bf.md>)

Recorded evaluation configuration: {"Synthetic images per tail class":500}. This record does not assert independent reproduction.

### ChimeraLoRA

Accuracy (Long): 88.8. Result ID: 699e53305698665ec412c007.

[Reporting paper](<https://www.sota2.com/research/paper/699d30a56017c4460ffab593.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699d30a56017c4460ffab593.md>)

Recorded evaluation configuration: {"Synthetic images per tail class":500}. This record does not assert independent reproduction.

### DataDream

Accuracy (Long): 88.7. Result ID: 699e53305698665ec412c005.

[Reporting paper](<https://www.sota2.com/research/paper/699d30a56017c4460ffab593.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa742a1e209131cea60278.md>)

Recorded evaluation configuration: {"Synthetic images per tail class":500}. This record does not assert independent reproduction.

### Real

Accuracy (Long): 78.8. Result ID: 699e53305698665ec412c004.

[Reporting paper](<https://www.sota2.com/research/paper/699d30a56017c4460ffab593.md>)

Recorded evaluation configuration: {"Synthetic images per tail class":0}. This record does not assert independent reproduction.

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