# Image Classification on Tiny ImageNet Step-Imbalance, p=100 (test)

Source: [Image Classification on Tiny ImageNet Step-Imbalance, p=100 (test)](<https://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-step-imbalance-p-100-test>)

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

Data updated: 2026-02-26T05:28:00.570Z

Evaluation of Image Classification performance on the test split of the Tiny ImageNet dataset configured with a Step-Imbalance distribution where p=100.

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) | Tiny ImageNet Step-Imbalance, p=100 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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-tiny-imagenet-step-imbalance-p-100-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| IB | 41.13 | Not recorded | 68fa6af71e209131cea2b6c4 |
| LDAM\* | 39.37 | Not recorded | 68fa6af71e209131cea2b6c4 |
| Focal | 38.24 | Not recorded | 68fa6af71e209131cea2b6c4 |
| CB | 37.35 | Not recorded | 68fa6af71e209131cea2b6c4 |
| Baseline (CE) | 36.74 | Not recorded | 68fa6af71e209131cea2b6c4 |

### IB

Accuracy: 41.13. Result ID: 698e47e7ffc3901de09c4a20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b6c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b6c4.md>)

[Implementation](<https://github.com/pseulki/IB-Loss>)

Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### LDAM\*

Accuracy: 39.37. Result ID: 698e47e7ffc3901de09c4a1f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b6c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### Focal

Accuracy: 38.24. Result ID: 698e47e7ffc3901de09c4a1d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b6c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa640c1e209131cea02556.md>)

[Implementation](<https://github.com/facebookresearch/Detectron>)

Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### CB

Accuracy: 37.35. Result ID: 698e47e7ffc3901de09c4a1e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b6c4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa654f1e209131cea0988a.md>)

[Implementation](<https://github.com/richardaecn/class-balanced-loss>)

Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### Baseline (CE)

Accuracy: 36.74. Result ID: 698e47e7ffc3901de09c4a1c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b6c4.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18"}. This record does not assert independent reproduction.

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