# Image Classification on ImageNet-1K (130 classes, continual learning stream)

Source: [Image Classification on ImageNet-1K (130 classes, continual learning stream)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-130-classes-continual-learning-stream>)

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

Data updated: 2026-04-01T06:41:54.419Z

Evaluation of Image Classification performance on a specific 130-class subset of ImageNet-1K, typically evaluated under a continual learning stream protocol.

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-1K 130 classes (continual learning stream) |
| Metric | Final Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Final Accuracy](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-130-classes-continual-learning-stream.md?metric=Final%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Final Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Baseline + Dynamic SSL + MLKD | 42 | Not recorded | 68fa7ad71e209131cea85779 |
| Baseline + MLKD | 39.82 | Not recorded | 68fa7ad71e209131cea85779 |
| Baseline + Dynamic SSL | 23.82 | Not recorded | 68fa7ad71e209131cea85779 |
| Baseline | 19.54 | Not recorded | 68fa7ad71e209131cea85779 |
| Fine-tuning | 5.82 | Not recorded | 68fa7ad71e209131cea85779 |

### Baseline + Dynamic SSL + MLKD

Final Accuracy: 42. Result ID: 69ccbc7047f34ce924b5c7e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad71e209131cea85779.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ad71e209131cea85779.md>)

Recorded evaluation configuration: {"backbone":"ResNet-18","components":"Dynamic SSL + MLKD","inference mode":"model ensemble"}. This record does not assert independent reproduction.

### Baseline + MLKD

Final Accuracy: 39.82. Result ID: 69ccbc7047f34ce924b5c7e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad71e209131cea85779.md>)

Recorded evaluation configuration: {"backbone":"ResNet-18","component":"MLKD"}. This record does not assert independent reproduction.

### Baseline + Dynamic SSL

Final Accuracy: 23.82. Result ID: 69ccbc7047f34ce924b5c7e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad71e209131cea85779.md>)

Recorded evaluation configuration: {"backbone":"ResNet-18","component":"Dynamic SSL"}. This record does not assert independent reproduction.

### Baseline

Final Accuracy: 19.54. Result ID: 69ccbc7047f34ce924b5c7e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad71e209131cea85779.md>)

Recorded evaluation configuration: {"backbone":"ResNet-18","memory buffer":"200 exemplars"}. This record does not assert independent reproduction.

### Fine-tuning

Final Accuracy: 5.82. Result ID: 69ccbc7047f34ce924b5c7e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ad71e209131cea85779.md>)

Recorded evaluation configuration: {"backbone":"ResNet-18"}. This record does not assert independent reproduction.

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