# Unsupervised Accuracy Estimation on Office-Home

Source: [Unsupervised Accuracy Estimation on Office-Home](<https://www.sota2.com/research/sota/unsupervised-accuracy-estimation-on-office-home>)

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

Data updated: 2026-02-26T06:00:52.918Z

Evaluation of model accuracy estimation capabilities on the Office-Home dataset under unsupervised conditions, reporting metrics such as R-squared (R^2) and associated p-values.

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 | Unsupervised Accuracy Estimation |
| Dataset (including any stated split) | Office-Home |
| Metric | R^2 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 36 of 36 |
| 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

- [R^2](<https://www.sota2.com/research/sota/unsupervised-accuracy-estimation-on-office-home.md?metric=R%5E2>): Higher is better; unit: SCALAR.

- [p-value](<https://www.sota2.com/research/sota/unsupervised-accuracy-estimation-on-office-home.md?metric=p-value>): Lower is better; unit: SCALAR.

## Recorded results

| Method | R^2 | Result date | Report paper |
| --- | --- | --- | --- |
| MANO | 0.926 | Not recorded | 68fa75d01e209131cea69ff5 |
| COT | 0.863 | Not recorded | 68fa75d01e209131cea69ff5 |
| COT | 0.863 | Not recorded | 68fa75d01e209131cea69ff5 |
| Rotation | 0.851 | Not recorded | 68fa75d01e209131cea69ff5 |
| MANO | 0.838 | Not recorded | 68fa75d01e209131cea69ff5 |
| Rotation | 0.823 | Not recorded | 68fa75d01e209131cea69ff5 |
| Rotation | 0.822 | Not recorded | 68fa75d01e209131cea69ff5 |
| MANO | 0.8 | Not recorded | 68fa75d01e209131cea69ff5 |
| ConfScore | 0.795 | Not recorded | 68fa75d01e209131cea69ff5 |
| ConfScore | 0.769 | Not recorded | 68fa75d01e209131cea69ff5 |
| Nuclear | 0.766 | Not recorded | 68fa75d01e209131cea69ff5 |
| COT | 0.762 | Not recorded | 68fa75d01e209131cea69ff5 |
| Entropy | 0.761 | Not recorded | 68fa75d01e209131cea69ff5 |
| Entropy | 0.742 | Not recorded | 68fa75d01e209131cea69ff5 |
| ConfScore | 0.741 | Not recorded | 68fa75d01e209131cea69ff5 |
| Nuclear | 0.731 | Not recorded | 68fa75d01e209131cea69ff5 |
| Entropy | 0.696 | Not recorded | 68fa75d01e209131cea69ff5 |
| Nuclear | 0.692 | Not recorded | 68fa75d01e209131cea69ff5 |
| Fréchet | 0.607 | Not recorded | 68fa75d01e209131cea69ff5 |
| Fréchet | 0.605 | Not recorded | 68fa75d01e209131cea69ff5 |
| Fréchet | 0.589 | Not recorded | 68fa75d01e209131cea69ff5 |
| ATC | 0.571 | Not recorded | 68fa75d01e209131cea69ff5 |
| ATC | 0.487 | Not recorded | 68fa75d01e209131cea69ff5 |
| Dispersion | 0.456 | Not recorded | 68fa75d01e209131cea69ff5 |
| Dispersion | 0.453 | Not recorded | 68fa75d01e209131cea69ff5 |
| Dispersion | 0.383 | Not recorded | 68fa75d01e209131cea69ff5 |
| ATC | 0.383 | Not recorded | 68fa75d01e209131cea69ff5 |
| MDE | 0.342 | Not recorded | 68fa75d01e209131cea69ff5 |
| MDE | 0.342 | Not recorded | 68fa75d01e209131cea69ff5 |
| MDE | 0.331 | Not recorded | 68fa75d01e209131cea69ff5 |
| ProjNorm | 0.172 | Not recorded | 68fa75d01e209131cea69ff5 |
| ProjNorm | 0.169 | Not recorded | 68fa75d01e209131cea69ff5 |
| AgreeScore | 0.132 | Not recorded | 68fa75d01e209131cea69ff5 |
| ProjNorm | 0.064 | Not recorded | 68fa75d01e209131cea69ff5 |
| AgreeScore | 0.054 | Not recorded | 68fa75d01e209131cea69ff5 |
| AgreeScore | 0.026 | Not recorded | 68fa75d01e209131cea69ff5 |

### MANO

R^2: 0.926. Result ID: 6993e6c53a6c3148491952f0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### COT

R^2: 0.863. Result ID: 6993e6c53a6c3148491952ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e815.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### COT

R^2: 0.863. Result ID: 6993e6c53a6c314849195306.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e815.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### Rotation

R^2: 0.851. Result ID: 6993e6c53a6c3148491952f1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea261a1.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### MANO

R^2: 0.838. Result ID: 6993e6c53a6c3148491952fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### Rotation

R^2: 0.823. Result ID: 6993e6c53a6c3148491952fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea261a1.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### Rotation

R^2: 0.822. Result ID: 6993e6c53a6c3148491952e5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea261a1.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### MANO

R^2: 0.8. Result ID: 6993e6c53a6c314849195308.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### ConfScore

R^2: 0.795. Result ID: 6993e6c53a6c3148491952e6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### ConfScore

R^2: 0.769. Result ID: 6993e6c53a6c3148491952f2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### Nuclear

R^2: 0.766. Result ID: 6993e6c53a6c314849195307.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e751e209131cea3ff83.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### COT

R^2: 0.762. Result ID: 6993e6c53a6c3148491952fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71021e209131cea4e815.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### Entropy

R^2: 0.761. Result ID: 6993e6c53a6c3148491952e7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9b1e209131cea29564.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### Entropy

R^2: 0.742. Result ID: 6993e6c53a6c3148491952f3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9b1e209131cea29564.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### ConfScore

R^2: 0.741. Result ID: 6993e6c53a6c3148491952fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### Nuclear

R^2: 0.731. Result ID: 6993e6c53a6c3148491952fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e751e209131cea3ff83.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### Entropy

R^2: 0.696. Result ID: 6993e6c53a6c3148491952ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a9b1e209131cea29564.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### Nuclear

R^2: 0.692. Result ID: 6993e6c53a6c3148491952ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e751e209131cea3ff83.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### Fréchet

R^2: 0.607. Result ID: 6993e6c53a6c3148491952f6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a091e209131cea25a4a.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### Fréchet

R^2: 0.605. Result ID: 6993e6c53a6c3148491952ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a091e209131cea25a4a.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### Fréchet

R^2: 0.589. Result ID: 6993e6c53a6c314849195302.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a091e209131cea25a4a.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### ATC

R^2: 0.571. Result ID: 6993e6c53a6c3148491952e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dab1e209131cea3b57f.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### ATC

R^2: 0.487. Result ID: 6993e6c53a6c3148491952f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dab1e209131cea3b57f.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### Dispersion

R^2: 0.456. Result ID: 6993e6c53a6c314849195303.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e42c.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### Dispersion

R^2: 0.453. Result ID: 6993e6c53a6c3148491952eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e42c.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### Dispersion

R^2: 0.383. Result ID: 6993e6c53a6c3148491952f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f21e209131cea4e42c.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### ATC

R^2: 0.383. Result ID: 6993e6c53a6c314849195301.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dab1e209131cea3b57f.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### MDE

R^2: 0.342. Result ID: 6993e6c53a6c3148491952f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727f1e209131cea56c3d.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### MDE

R^2: 0.342. Result ID: 6993e6c53a6c314849195305.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727f1e209131cea56c3d.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### MDE

R^2: 0.331. Result ID: 6993e6c53a6c3148491952ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa727f1e209131cea56c3d.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### ProjNorm

R^2: 0.172. Result ID: 6993e6c53a6c314849195304.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bc01e209131cea30105.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### ProjNorm

R^2: 0.169. Result ID: 6993e6c53a6c3148491952f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bc01e209131cea30105.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

### AgreeScore

R^2: 0.132. Result ID: 6993e6c53a6c314849195300.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c811e209131cea34627.md>)

Recorded evaluation configuration: {"Model":"WRN-50-2"}. This record does not assert independent reproduction.

### ProjNorm

R^2: 0.064. Result ID: 6993e6c53a6c3148491952ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bc01e209131cea30105.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### AgreeScore

R^2: 0.054. Result ID: 6993e6c53a6c3148491952e8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c811e209131cea34627.md>)

Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction.

### AgreeScore

R^2: 0.026. Result ID: 6993e6c53a6c3148491952f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75d01e209131cea69ff5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c811e209131cea34627.md>)

Recorded evaluation configuration: {"Model":"ResNet50"}. This record does not assert independent reproduction.

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