# Machine Unlearning on ImageNet-1K

Source: [Machine Unlearning on ImageNet-1K](<https://www.sota2.com/research/sota/machine-unlearning-on-imagenet-1k>)

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

Data updated: 2026-02-26T05:40:49.308Z

Evaluation of Machine Unlearning performance on the standard ImageNet-1K dataset, measured using metrics related to forgetting (Df, Dr) and utility retention (Dft, Drt, HM, HMl).

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 | Machine Unlearning |
| Dataset (including any stated split) | ImageNet-1K |
| Metric | Df |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Df](<https://www.sota2.com/research/sota/machine-unlearning-on-imagenet-1k.md?metric=Df>): Higher is better; unit: PERCENT.

- [Dr](<https://www.sota2.com/research/sota/machine-unlearning-on-imagenet-1k.md?metric=Dr>): Higher is better; unit: PERCENT.

- [Dft](<https://www.sota2.com/research/sota/machine-unlearning-on-imagenet-1k.md?metric=Dft>): Higher is better; unit: PERCENT.

- [Drt](<https://www.sota2.com/research/sota/machine-unlearning-on-imagenet-1k.md?metric=Drt>): Higher is better; unit: PERCENT.

- [HM](<https://www.sota2.com/research/sota/machine-unlearning-on-imagenet-1k.md?metric=HM>): Higher is better; unit: PERCENT.

- [HMl](<https://www.sota2.com/research/sota/machine-unlearning-on-imagenet-1k.md?metric=HMl>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Df | Result date | Report paper |
| --- | --- | --- | --- |
| Original | 87.8 | Not recorded | 68fa77cb1e209131cea75615 |
| ESC | 0.11 | Not recorded | 68fa77cb1e209131cea75615 |
| ESC-T | 0.01 | Not recorded | 68fa77cb1e209131cea75615 |
| LAU | 0 | Not recorded | 68fa77cb1e209131cea75615 |

### Original

Df: 87.8. Result ID: 69956b233badfaffe65f5065.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

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

### ESC

Df: 0.11. Result ID: 69956b233badfaffe65f5067.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Implementation](<https://github.com/KU-VGI/ESC>)

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

### ESC-T

Df: 0.01. Result ID: 69956b233badfaffe65f5068.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Implementation](<https://github.com/KU-VGI/ESC>)

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

### LAU

Df: 0. Result ID: 69956b233badfaffe65f5066.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a21e209131cea52359.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.