# Image Classification on ImageNet-100 (40-20 split)

Source: [Image Classification on ImageNet-100 (40-20 split)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-40-20-split>)

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

Data updated: 2026-02-26T05:34:24.286Z

Evaluation of Image Classification performance on the specific 40-20 split configuration of the ImageNet-100 dataset.

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-100 (40-20 split) |
| Metric | Accuracy (R) |
| 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

- [Accuracy (R)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-40-20-split.md?metric=Accuracy%20(R)>): Higher is better; unit: PERCENT.

- [H Score](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-40-20-split.md?metric=H%20Score>): Higher is better; unit: SCALAR.

- [F1 Score](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-40-20-split.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Accuracy (Overall)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-100-40-20-split.md?metric=Accuracy%20(Overall)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (R) | Result date | Report paper |
| --- | --- | --- | --- |
| GS-LORA | 82.7 | Not recorded | 68fa74251e209131cea5ff6b |
| MAS\* | 80.2 | Not recorded | 68fa74251e209131cea5ff6b |
| EWC\* | 80 | Not recorded | 68fa74251e209131cea5ff6b |
| Pre-train | 76.5 | Not recorded | 68fa74251e209131cea5ff6b |
| L2\* | 74.7 | Not recorded | 68fa74251e209131cea5ff6b |
| Retrain | 46.1 | Not recorded | 68fa74251e209131cea5ff6b |

### GS-LORA

Accuracy (R): 82.7. Result ID: 699332893a6c314849145de6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Implementation](<https://github.com/bjzhb666/GS-LoRA>)

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

### MAS\*

Accuracy (R): 80.2. Result ID: 699332893a6c314849145de4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e61e209131cea073fa.md>)

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

### EWC\*

Accuracy (R): 80. Result ID: 699332893a6c314849145de3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3555e.md>)

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

### Pre-train

Accuracy (R): 76.5. Result ID: 699332893a6c314849145de1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

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

### L2\*

Accuracy (R): 74.7. Result ID: 699332893a6c314849145de2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

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

### Retrain

Accuracy (R): 46.1. Result ID: 699332893a6c314849145de5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74251e209131cea5ff6b.md>)

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

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