# Semantic Segmentation on ACDC Rain (test)

Source: [Semantic Segmentation on ACDC Rain (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-acdc-rain-test>)

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

Data updated: 2026-04-03T07:44:45.332Z

Evaluation of Semantic Segmentation performance on the ACDC dataset, specifically focusing on the Rain condition within the test split, reporting learning accuracy and average forgetting metrics.

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 | Semantic Segmentation |
| Dataset (including any stated split) | ACDC Rain (test) |
| Metric | Learning Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Learning Accuracy](<https://www.sota2.com/research/sota/semantic-segmentation-on-acdc-rain-test.md?metric=Learning%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Forgetting](<https://www.sota2.com/research/sota/semantic-segmentation-on-acdc-rain-test.md?metric=Average%20Forgetting>): Lower is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/semantic-segmentation-on-acdc-rain-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Learning Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DINO + AutoAlb + CN | 71 | Not recorded | 68fa6fbf1e209131cea47329 |
| Replay + DINO | 70.8 | Not recorded | 68fa6fbf1e209131cea47329 |
| Replay + AutoAlb + CN | 69.9 | Not recorded | 68fa6fbf1e209131cea47329 |
| EWC + AutoAlb + CN | 69.1 | Not recorded | 68fa6fbf1e209131cea47329 |
| EWC + DINO | 66 | Not recorded | 68fa6fbf1e209131cea47329 |
| Replay | 64.2 | Not recorded | 68fa6fbf1e209131cea47329 |
| EWC | 61.4 | Not recorded | 68fa6fbf1e209131cea47329 |

### DINO + AutoAlb + CN

Learning Accuracy: 71. Result ID: 6990ea4b3a6c314849044293.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Implementation](<https://www.sota2.com/github.com/tobiaskalb/feature-reuse-css>)

Recorded evaluation configuration: {"SSL Pre-training":"DINO","Augmentation":"AutoAlb","Normalisation":"CN"}. This record does not assert independent reproduction.

### Replay + DINO

Learning Accuracy: 70.8. Result ID: 6990ea4b3a6c314849044291.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Implementation](<https://www.sota2.com/github.com/tobiaskalb/feature-reuse-css>)

Recorded evaluation configuration: {"SSL Pre-training":"DINO"}. This record does not assert independent reproduction.

### Replay + AutoAlb + CN

Learning Accuracy: 69.9. Result ID: 6990ea4b3a6c314849044292.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Implementation](<https://www.sota2.com/github.com/tobiaskalb/feature-reuse-css>)

Recorded evaluation configuration: {"Augmentation":"AutoAlb","Normalisation":"CN"}. This record does not assert independent reproduction.

### EWC + AutoAlb + CN

Learning Accuracy: 69.1. Result ID: 6990ea4b3a6c31484904428f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Implementation](<https://www.sota2.com/github.com/tobiaskalb/feature-reuse-css>)

Recorded evaluation configuration: {"Augmentation":"AutoAlb","Normalisation":"CN"}. This record does not assert independent reproduction.

### EWC + DINO

Learning Accuracy: 66. Result ID: 6990ea4b3a6c31484904428e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Implementation](<https://www.sota2.com/github.com/tobiaskalb/feature-reuse-css>)

Recorded evaluation configuration: {"SSL Pre-training":"DINO"}. This record does not assert independent reproduction.

### Replay

Learning Accuracy: 64.2. Result ID: 6990ea4b3a6c314849044290.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d711e209131cea39eba.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### EWC

Learning Accuracy: 61.4. Result ID: 6990ea4b3a6c31484904428d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fbf1e209131cea47329.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3555e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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