# Image Classification on ImageNet 2 imgs/cls (train/val)

Source: [Image Classification on ImageNet 2 imgs/cls (train/val)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-2-imgs-cls-train-val>)

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

Data updated: 2026-02-26T06:06:44.269Z

Evaluation of Image Classification performance on the ImageNet 2 imgs/cls subset, using the combined training and validation splits.

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 2 imgs/cls (train/val) |
| Metric | Top-1 Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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-2-imgs-cls-train-val.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc | Result date | Report paper |
| --- | --- | --- | --- |
| iBOT-vMF | 61.1 | Not recorded | 68fa733f1e209131cea5b3cc |
| DINO-vMF | 59.3 | Not recorded | 68fa733f1e209131cea5b3cc |
| MSN | 58.9 | Not recorded | 68fa733f1e209131cea5b3cc |
| iBOT | 56 | Not recorded | 68fa733f1e209131cea5b3cc |
| MSN | 55.8 | Not recorded | 68fa733f1e209131cea5b3cc |
| DINO | 51.9 | Not recorded | 68fa733f1e209131cea5b3cc |
| DINO-vMF | 49.4 | Not recorded | 68fa733f1e209131cea5b3cc |
| DINO | 48.9 | Not recorded | 68fa733f1e209131cea5b3cc |

### iBOT-vMF

Top-1 Acc: 61.1. Result ID: 6992b18e3a6c31484910c7a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-Base/16","Evaluation Protocol":"Linear Classification"}. This record does not assert independent reproduction.

### DINO-vMF

Top-1 Acc: 59.3. Result ID: 6992b18e3a6c31484910c7a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-Base/16","Evaluation Protocol":"Linear Classification"}. This record does not assert independent reproduction.

### MSN

Top-1 Acc: 58.9. Result ID: 6992b18e3a6c31484910c7a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-Base/16","Evaluation Protocol":"Linear Classification"}. This record does not assert independent reproduction.

### iBOT

Top-1 Acc: 56. Result ID: 6992b18e3a6c31484910c7a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

Recorded evaluation configuration: {"Architecture":"ViT-Base/16","Evaluation Protocol":"Linear Classification"}. This record does not assert independent reproduction.

### MSN

Top-1 Acc: 55.8. Result ID: 6992b18e3a6c31484910c7a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c591e209131cea33793.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-Small/16","Evaluation Protocol":"Linear Classification"}. This record does not assert independent reproduction.

### DINO

Top-1 Acc: 51.9. Result ID: 6992b18e3a6c31484910c7a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea2594c.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-Base/16","Evaluation Protocol":"Linear Classification"}. This record does not assert independent reproduction.

### DINO-vMF

Top-1 Acc: 49.4. Result ID: 6992b18e3a6c31484910c7a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-Small/16","Evaluation Protocol":"Linear Classification"}. This record does not assert independent reproduction.

### DINO

Top-1 Acc: 48.9. Result ID: 6992b18e3a6c31484910c7a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa733f1e209131cea5b3cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a071e209131cea2594c.md>)

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

Recorded evaluation configuration: {"Architecture":"ViT-Small/16","Evaluation Protocol":"Linear Classification"}. This record does not assert independent reproduction.

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