# Continual Learning on ImageNet-R 50 tasks

Source: [Continual Learning on ImageNet-R 50 tasks](<https://www.sota2.com/research/sota/continual-learning-on-imagenet-r-50-tasks>)

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

Data updated: 2026-05-11T09:15:02.083Z

Evaluation of Continual Learning performance on the ImageNet-R dataset structured across 50 tasks, measured using Accuracy and Forgetting.

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 | Continual Learning |
| Dataset (including any stated split) | ImageNet-R 50 tasks |
| Metric | Accuracy (Last Task) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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 (Last Task)](<https://www.sota2.com/research/sota/continual-learning-on-imagenet-r-50-tasks.md?metric=Accuracy%20(Last%20Task)>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/continual-learning-on-imagenet-r-50-tasks.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Forgetting](<https://www.sota2.com/research/sota/continual-learning-on-imagenet-r-50-tasks.md?metric=Forgetting>): Lower is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/continual-learning-on-imagenet-r-50-tasks.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Last Task) | Result date | Report paper |
| --- | --- | --- | --- |
| SR2-LoRA | 74.85 | Not recorded | 6a01626bdbc836b87d822fb2 |
| SSIAT | 74.52 | Not recorded | 6a01626bdbc836b87d822fb2 |
| LoRA-DRS | 72.17 | Not recorded | 6a01626bdbc836b87d822fb2 |
| MACIL | 70.1 | Not recorded | 6a01626bdbc836b87d822fb2 |
| SLCA | 68.95 | Not recorded | 6a01626bdbc836b87d822fb2 |
| EASE | 68.53 | Not recorded | 6a01626bdbc836b87d822fb2 |
| CL-LoRA | 68.36 | Not recorded | 6a01626bdbc836b87d822fb2 |
| MOS | 66.92 | Not recorded | 6a01626bdbc836b87d822fb2 |
| InfLoRA | 61.91 | Not recorded | 6a01626bdbc836b87d822fb2 |
| CODA-Prompt | 48.89 | Not recorded | 6a01626bdbc836b87d822fb2 |

### SR2-LoRA

Accuracy (Last Task): 74.85. Result ID: 6a019dfc47f34ce924e3ba50.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### SSIAT

Accuracy (Last Task): 74.52. Result ID: 6a019dfc47f34ce924e3ba4b.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### LoRA-DRS

Accuracy (Last Task): 72.17. Result ID: 6a019dfc47f34ce924e3ba4d.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77bc1e209131cea75057.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### MACIL

Accuracy (Last Task): 70.1. Result ID: 6a019dfc47f34ce924e3ba4f.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77081e209131cea70a04.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### SLCA

Accuracy (Last Task): 68.95. Result ID: 6a019dfc47f34ce924e3ba48.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70c91e209131cea4d120.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### EASE

Accuracy (Last Task): 68.53. Result ID: 6a019dfc47f34ce924e3ba4a.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72981e209131cea57699.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### CL-LoRA

Accuracy (Last Task): 68.36. Result ID: 6a019dfc47f34ce924e3ba4c.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb1b.md>)

[Implementation](<https://github.com/JiangpengHe/CL-LoRA>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### MOS

Accuracy (Last Task): 66.92. Result ID: 6a019dfc47f34ce924e3ba4e.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa797b1e209131cea7dbd3.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### InfLoRA

Accuracy (Last Task): 61.91. Result ID: 6a019dfc47f34ce924e3ba49.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bb1e209131cea58354.md>)

[Implementation](<https://github.com/liangyanshuo/InfLoRA>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

### CODA-Prompt

Accuracy (Last Task): 48.89. Result ID: 6a019dfc47f34ce924e3ba47.

[Reporting paper](<https://www.sota2.com/research/paper/6a01626bdbc836b87d822fb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee41e209131cea42add.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16-IN21K","Number of Tasks":"50"}. This record does not assert independent reproduction.

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