# Image Classification on ImageNet LT (Sampling Factor Evaluation)

Source: [Image Classification on ImageNet LT (Sampling Factor Evaluation)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-lt-sampling-factor-evaluation>)

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

Data updated: 2026-04-03T08:28:43.914Z

Evaluation of Image Classification performance on the ImageNet-LT dataset, focusing on Top-1 Accuracy measured across different sampling factors (s=1.0, 0.75, 0.50, 0.25, 0.125).

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 |
| Metric | Top-1 Accuracy (s=1.0) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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 Accuracy (s=1.0)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-lt-sampling-factor-evaluation.md?metric=Top-1%20Accuracy%20(s%3D1.0)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (s=0.75)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-lt-sampling-factor-evaluation.md?metric=Top-1%20Accuracy%20(s%3D0.75)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (s=0.50)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-lt-sampling-factor-evaluation.md?metric=Top-1%20Accuracy%20(s%3D0.50)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (s=0.25)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-lt-sampling-factor-evaluation.md?metric=Top-1%20Accuracy%20(s%3D0.25)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (s=0.125)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-lt-sampling-factor-evaluation.md?metric=Top-1%20Accuracy%20(s%3D0.125)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (s=1.0) | Result date | Report paper |
| --- | --- | --- | --- |
| Ours(Sum) | 52.9 | Not recorded | 68fa7b471e209131cea877ef |
| MoCoV2 | 49.5 | Not recorded | 68fa7b471e209131cea877ef |
| SimCLR | 46.81 | Not recorded | 68fa7b471e209131cea877ef |
| SDCLR | 46.62 | Not recorded | 68fa7b471e209131cea877ef |
| Byol | 43.16 | Not recorded | 68fa7b471e209131cea877ef |
| VicReg | 38.24 | Not recorded | 68fa7b471e209131cea877ef |

### Ours(Sum)

Top-1 Accuracy (s=1.0): 52.9. Result ID: 69cf7a2347f34ce924b955a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b471e209131cea877ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b471e209131cea877ef.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"Linear Evaluation"}. This record does not assert independent reproduction.

### MoCoV2

Top-1 Accuracy (s=1.0): 49.5. Result ID: 69cf7a2347f34ce924b955a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b471e209131cea877ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa673f1e209131cea15344.md>)

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

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"Linear Evaluation"}. This record does not assert independent reproduction.

### SimCLR

Top-1 Accuracy (s=1.0): 46.81. Result ID: 69cf7a2347f34ce924b955a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b471e209131cea877ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d71e209131cea18de5.md>)

[Implementation](<https://github.com/google-research/simclr>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"Linear Evaluation"}. This record does not assert independent reproduction.

### SDCLR

Top-1 Accuracy (s=1.0): 46.62. Result ID: 69cf7a2347f34ce924b955a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b471e209131cea877ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a221e209131cea263d6.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"Linear Evaluation"}. This record does not assert independent reproduction.

### Byol

Top-1 Accuracy (s=1.0): 43.16. Result ID: 69cf7a2347f34ce924b955a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b471e209131cea877ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684a1e209131cea1b1e9.md>)

[Implementation](<https://github.com/deepmind/deepmind-research/tree/byol>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"Linear Evaluation"}. This record does not assert independent reproduction.

### VicReg

Top-1 Accuracy (s=1.0): 38.24. Result ID: 69cf7a2347f34ce924b955a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b471e209131cea877ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bb91e209131cea2fe0f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Evaluation Protocol":"Linear Evaluation"}. This record does not assert independent reproduction.

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