# Image Classification on ImageNet-LT Uniform Shifted (test)

Source: [Image Classification on ImageNet-LT Uniform Shifted (test)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-lt-uniform-shifted-test>)

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

Data updated: 2026-02-26T06:06:49.640Z

Evaluation of Image Classification performance on the test split of the ImageNet-LT dataset configured with a Uniform Shift distribution.

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-LT Uniform Shifted (test) |
| Metric | Top-1 Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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 Acc](<https://www.sota2.com/research/sota/image-classification-on-imagenet-lt-uniform-shifted-test.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc | Result date | Report paper |
| --- | --- | --- | --- |
| DiVE | 53.1 | Not recorded | 68fa6acb1e209131cea2a4a4 |
| DiVE | 53.1 | Not recorded | 68fa6acb1e209131cea2a4a4 |
| LADE | 53 | Not recorded | 68fa698d1e209131cea228f0 |
| PC Softmax | 52.8 | Not recorded | 68fa698d1e209131cea228f0 |
| Balanced Softmax | 52.1 | Not recorded | 68fa698d1e209131cea228f0 |
| PC Balanced Softmax | 52.1 | Not recorded | 68fa698d1e209131cea228f0 |
| Causal Norm | 52 | Not recorded | 68fa698d1e209131cea228f0 |
| PC Causal Norm | 52 | Not recorded | 68fa698d1e209131cea228f0 |
| BSCE | 50.48 | Not recorded | 68fa6acb1e209131cea2a4a4 |
| BSCE | 50.48 | Not recorded | 68fa6acb1e209131cea2a4a4 |
| CE | 49.33 | Not recorded | 68fa6acb1e209131cea2a4a4 |
| Softmax | 48.2 | Not recorded | 68fa698d1e209131cea228f0 |
| CE | 43.89 | Not recorded | 68fa6acb1e209131cea2a4a4 |

### DiVE

Top-1 Acc: 53.1. Result ID: 699ad1d75698665ec460df87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4a4.md>)

Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction.

### DiVE

Top-1 Acc: 53.1. Result ID: 699ad1d75698665ec460df8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4a4.md>)

Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction.

### LADE

Top-1 Acc: 53. Result ID: 698db42e8b517eb4332336e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Implementation](<https://github.com/hyperconnect/LADE>)

Recorded evaluation configuration: {"Post-prior Correction (PC)":"implicit","Training Epochs":180}. This record does not assert independent reproduction.

### PC Softmax

Top-1 Acc: 52.8. Result ID: 698db42e8b517eb4332336e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Implementation](<https://github.com/hyperconnect/LADE>)

Recorded evaluation configuration: {"Post-prior Correction (PC)":true,"Training Epochs":180}. This record does not assert independent reproduction.

### Balanced Softmax

Top-1 Acc: 52.1. Result ID: 698db42e8b517eb4332336e4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c11e209131cea1e125.md>)

[Implementation](<https://github.com/jiawei-ren/BalancedMetaSoftmax>)

Recorded evaluation configuration: {"Post-prior Correction (PC)":false,"Training Epochs":180}. This record does not assert independent reproduction.

### PC Balanced Softmax

Top-1 Acc: 52.1. Result ID: 698db42e8b517eb4332336e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Implementation](<https://github.com/hyperconnect/LADE>)

Recorded evaluation configuration: {"Post-prior Correction (PC)":true,"Training Epochs":180}. This record does not assert independent reproduction.

### Causal Norm

Top-1 Acc: 52. Result ID: 698db42e8b517eb4332336e3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa694e1e209131cea21632.md>)

[Implementation](<https://github.com/KaihuaTang/Long-Tailed-Recognition.pytorch>)

Recorded evaluation configuration: {"Post-prior Correction (PC)":false,"Training Epochs":180}. This record does not assert independent reproduction.

### PC Causal Norm

Top-1 Acc: 52. Result ID: 698db42e8b517eb4332336e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

[Implementation](<https://github.com/hyperconnect/LADE>)

Recorded evaluation configuration: {"Post-prior Correction (PC)":true,"Training Epochs":180}. This record does not assert independent reproduction.

### BSCE

Top-1 Acc: 50.48. Result ID: 699ad1d75698665ec460df86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c11e209131cea1e125.md>)

[Implementation](<https://github.com/jiawei-ren/BalancedMetaSoftmax>)

Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction.

### BSCE

Top-1 Acc: 50.48. Result ID: 699ad1d75698665ec460df89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c11e209131cea1e125.md>)

[Implementation](<https://github.com/jiawei-ren/BalancedMetaSoftmax>)

Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction.

### CE

Top-1 Acc: 49.33. Result ID: 699ad1d75698665ec460df88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4a4.md>)

Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":true}. This record does not assert independent reproduction.

### Softmax

Top-1 Acc: 48.2. Result ID: 698db42e8b517eb4332336e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa698d1e209131cea228f0.md>)

Recorded evaluation configuration: {"Post-prior Correction (PC)":false,"Training Epochs":180}. This record does not assert independent reproduction.

### CE

Top-1 Acc: 43.89. Result ID: 699ad1d75698665ec460df85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6acb1e209131cea2a4a4.md>)

Recorded evaluation configuration: {"Training epochs":90,"Post-compensation":false}. This record does not assert independent reproduction.

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