# Semi-supervised Continual Learning on Tiny-ImageNet 10-class 32x32

Source: [Semi-supervised Continual Learning on Tiny-ImageNet 10-class 32x32](<https://www.sota2.com/research/sota/semi-supervised-continual-learning-on-tiny-imagenet-10-class-32x32>)

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

Data updated: 2026-02-26T05:34:10.341Z

Evaluation of Semi-supervised Continual Learning performance on the Tiny-ImageNet 10-class 32x32 dataset, tracking accuracy across sequential batches.

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 | Semi-supervised Continual Learning |
| Dataset (including any stated split) | Tiny-ImageNet 10-class 32x32 |
| Metric | Accuracy (Batch 1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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 (Batch 1)](<https://www.sota2.com/research/sota/semi-supervised-continual-learning-on-tiny-imagenet-10-class-32x32.md?metric=Accuracy%20(Batch%201)>): Higher is better; unit: PERCENT.

- [Accuracy (Batch 2)](<https://www.sota2.com/research/sota/semi-supervised-continual-learning-on-tiny-imagenet-10-class-32x32.md?metric=Accuracy%20(Batch%202)>): Higher is better; unit: PERCENT.

- [Accuracy (Batch 3)](<https://www.sota2.com/research/sota/semi-supervised-continual-learning-on-tiny-imagenet-10-class-32x32.md?metric=Accuracy%20(Batch%203)>): Higher is better; unit: PERCENT.

- [Accuracy (Batch 4)](<https://www.sota2.com/research/sota/semi-supervised-continual-learning-on-tiny-imagenet-10-class-32x32.md?metric=Accuracy%20(Batch%204)>): Higher is better; unit: PERCENT.

- [Accuracy (Batch 5)](<https://www.sota2.com/research/sota/semi-supervised-continual-learning-on-tiny-imagenet-10-class-32x32.md?metric=Accuracy%20(Batch%205)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Batch 1) | Result date | Report paper |
| --- | --- | --- | --- |
| ORDisCo | 45.2 | Not recorded | 68fa6bd61e209131cea30770 |
| SMB+UMB | 43.8 | Not recorded | 68fa6bd61e209131cea30770 |
| SMB | 43 | Not recorded | 68fa6bd61e209131cea30770 |

### ORDisCo

Accuracy (Batch 1): 45.2. Result ID: 698ea469ffc3901de09f648b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd61e209131cea30770.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd61e209131cea30770.md>)

Recorded evaluation configuration: {"Classes":10,"Resolution":"32x32"}. This record does not assert independent reproduction.

### SMB+UMB

Accuracy (Batch 1): 43.8. Result ID: 698ea469ffc3901de09f648a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd61e209131cea30770.md>)

Recorded evaluation configuration: {"Classes":10,"Resolution":"32x32"}. This record does not assert independent reproduction.

### SMB

Accuracy (Batch 1): 43. Result ID: 698ea469ffc3901de09f6489.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6bd61e209131cea30770.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634e1e209131ce9fded4.md>)

Recorded evaluation configuration: {"Classes":10,"Resolution":"32x32"}. This record does not assert independent reproduction.

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