# Multi-source Domain Adaptation on PACS (test)

Source: [Multi-source Domain Adaptation on PACS (test)](<https://www.sota2.com/research/sota/multi-source-domain-adaptation-on-pacs-test>)

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

Data updated: 2026-02-26T05:34:08.819Z

Evaluation of Multi-source Domain Adaptation performance on the test split of the PACS dataset, reporting domain-specific accuracies (Art, Cartoon, Sketch, Photo) and the average.

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 | Multi-source Domain Adaptation |
| Dataset (including any stated split) | PACS (test) |
| Metric | Accuracy (Art) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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 (Art)](<https://www.sota2.com/research/sota/multi-source-domain-adaptation-on-pacs-test.md?metric=Accuracy%20(Art)>): Higher is better; unit: PERCENT.

- [Accuracy (Cartoon)](<https://www.sota2.com/research/sota/multi-source-domain-adaptation-on-pacs-test.md?metric=Accuracy%20(Cartoon)>): Higher is better; unit: PERCENT.

- [Accuracy (Sketch)](<https://www.sota2.com/research/sota/multi-source-domain-adaptation-on-pacs-test.md?metric=Accuracy%20(Sketch)>): Higher is better; unit: PERCENT.

- [Accuracy (Photo)](<https://www.sota2.com/research/sota/multi-source-domain-adaptation-on-pacs-test.md?metric=Accuracy%20(Photo)>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/multi-source-domain-adaptation-on-pacs-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Art) | Result date | Report paper |
| --- | --- | --- | --- |
| DSBN | 88.94 | Not recorded | 68fa68071e209131cea199fa |
| SIB-Rot | 88.9 | Not recorded | 68fa676c1e209131cea1610f |
| Rot | 88.7 | Not recorded | 68fa676c1e209131cea1610f |
| DSON | 86.54 | Not recorded | 68fa68071e209131cea199fa |
| SIB-Rot | 85.7 | Not recorded | 68fa676c1e209131cea1610f |
| JiGen | 84.9 | Not recorded | 68fa676c1e209131cea1610f |
| SN | 79 | Not recorded | 68fa68071e209131cea199fa |
| Baseline | 78.85 | Not recorded | 68fa68071e209131cea199fa |

### DSBN

Accuracy (Art): 88.94. Result ID: 698d54408b517eb43320aed3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68071e209131cea199fa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e11e209131cea0d171.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Algorithm":"Shu et al. \[26\]"}. This record does not assert independent reproduction.

### SIB-Rot

Accuracy (Art): 88.9. Result ID: 698d33a48b517eb4331fc229.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1610f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1610f.md>)

[Implementation](<https://github.com/amzn/xfer>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","K":"3"}. This record does not assert independent reproduction.

### Rot

Accuracy (Art): 88.7. Result ID: 698d33a48b517eb4331fc227.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1610f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66c81e209131cea12376.md>)

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

### DSON

Accuracy (Art): 86.54. Result ID: 698d54408b517eb43320aed5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68071e209131cea199fa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68071e209131cea199fa.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Algorithm":"Shu et al. \[26\]"}. This record does not assert independent reproduction.

### SIB-Rot

Accuracy (Art): 85.7. Result ID: 698d33a48b517eb4331fc228.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1610f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1610f.md>)

[Implementation](<https://github.com/amzn/xfer>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","K":"0"}. This record does not assert independent reproduction.

### JiGen

Accuracy (Art): 84.9. Result ID: 698d33a48b517eb4331fc226.

[Reporting paper](<https://www.sota2.com/research/paper/68fa676c1e209131cea1610f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66391e209131cea0ef3c.md>)

[Implementation](<https://github.com/fmcarlucci/JigenDG>)

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

### SN

Accuracy (Art): 79. Result ID: 698d54408b517eb43320aed4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68071e209131cea199fa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65aa1e209131cea0bbfa.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Algorithm":"Shu et al. \[26\]"}. This record does not assert independent reproduction.

### Baseline

Accuracy (Art): 78.85. Result ID: 698d54408b517eb43320aed2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa68071e209131cea199fa.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Algorithm":"Shu et al. \[26\]"}. This record does not assert independent reproduction.

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