# Single-class Unlearning on Tiny ImageNet (test)

Source: [Single-class Unlearning on Tiny ImageNet (test)](<https://www.sota2.com/research/sota/single-class-unlearning-on-tiny-imagenet-test>)

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

Data updated: 2026-02-26T05:21:33.556Z

Evaluation of Single-class Unlearning performance on the test split of the Tiny ImageNet dataset, measured using specific accuracy retention and forgetting metrics (Acc\_f, Acc\_r, MIA).

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 | Single-class Unlearning |
| Dataset (including any stated split) | Tiny ImageNet (test) |
| Metric | Accuracy Forgotten |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 0 of 0 |
| 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 Forgotten](<https://www.sota2.com/research/sota/single-class-unlearning-on-tiny-imagenet-test.md?metric=Accuracy%20Forgotten>): Higher is better; unit: PERCENT.

- [Accuracy Retained](<https://www.sota2.com/research/sota/single-class-unlearning-on-tiny-imagenet-test.md?metric=Accuracy%20Retained>): Higher is better; unit: PERCENT.

- [Accuracy Forgotten (Test)](<https://www.sota2.com/research/sota/single-class-unlearning-on-tiny-imagenet-test.md?metric=Accuracy%20Forgotten%20(Test)>): Higher is better; unit: PERCENT.

- [Accuracy Retained (Test)](<https://www.sota2.com/research/sota/single-class-unlearning-on-tiny-imagenet-test.md?metric=Accuracy%20Retained%20(Test)>): Higher is better; unit: PERCENT.

- [Harmonic Mean](<https://www.sota2.com/research/sota/single-class-unlearning-on-tiny-imagenet-test.md?metric=Harmonic%20Mean>): Higher is better; unit: SCALAR.

- [MIA](<https://www.sota2.com/research/sota/single-class-unlearning-on-tiny-imagenet-test.md?metric=MIA>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy Forgotten | Result date | Report paper |
| --- | --- | --- | --- |

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