# Semantic Segmentation on PASCAL-Context (pAcc/mAcc metrics)

Source: [Semantic Segmentation on PASCAL-Context (pAcc/mAcc metrics)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-pacc-macc-metrics>)

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

Data updated: 2026-02-26T06:11:14.155Z

Evaluation of Semantic Segmentation performance on the PASCAL Context dataset, reporting pixel accuracy (pAcc) and mean accuracy (mAcc) variants.

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) | PASCAL-Context |
| Metric | pAcc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [pAcc](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-pacc-macc-metrics.md?metric=pAcc>): Higher is better; unit: PERCENT.

- [pAcc (s)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-pacc-macc-metrics.md?metric=pAcc%20(s)>): Higher is better; unit: PERCENT.

- [pAcc (u)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-pacc-macc-metrics.md?metric=pAcc%20(u)>): Higher is better; unit: PERCENT.

- [mAcc (s)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-pacc-macc-metrics.md?metric=mAcc%20(s)>): Higher is better; unit: PERCENT.

- [mAcc (u)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-pacc-macc-metrics.md?metric=mAcc%20(u)>): Higher is better; unit: PERCENT.

- [mAcc](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-context-pacc-macc-metrics.md?metric=mAcc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | pAcc | Result date | Report paper |
| --- | --- | --- | --- |
| MaskCLIP+ | 74.8 | Not recorded | 68fa6d1f1e209131cea37ece |
| Fully Sup. | 74.8 | Not recorded | 68fa6d1f1e209131cea37ece |
| CaGNet | 56.6 | Not recorded | 68fa6d1f1e209131cea37ece |
| ZS3Net | 52.8 | Not recorded | 68fa6d1f1e209131cea37ece |
| ZS3Net | 49.5 | Not recorded | 68fa6d1f1e209131cea37ece |

### MaskCLIP+

pAcc: 74.8. Result ID: 698f936c3a6c314849fa3e97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ece.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ece.md>)

Recorded evaluation configuration: {"inference\_mode":"transductive"}. This record does not assert independent reproduction.

### Fully Sup.

pAcc: 74.8. Result ID: 698f936c3a6c314849fa3e98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ece.md>)

Recorded evaluation configuration: {"supervision":"fully supervised"}. This record does not assert independent reproduction.

### CaGNet

pAcc: 56.6. Result ID: 698f936c3a6c314849fa3e95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ece.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68271e209131cea1a52e.md>)

[Implementation](<https://github.com/bcmi/CaGNet-Zero-Shot-Semantic-Segmentation>)

Recorded evaluation configuration: {"inference\_mode":"inductive"}. This record does not assert independent reproduction.

### ZS3Net

pAcc: 52.8. Result ID: 698f936c3a6c314849fa3e94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ece.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66a91e209131cea11731.md>)

[Implementation](<https://github.com/valeoai/ZS3>)

Recorded evaluation configuration: {"inference\_mode":"inductive"}. This record does not assert independent reproduction.

### ZS3Net

pAcc: 49.5. Result ID: 698f936c3a6c314849fa3e96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d1f1e209131cea37ece.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66a91e209131cea11731.md>)

[Implementation](<https://github.com/valeoai/ZS3>)

Recorded evaluation configuration: {"inference\_mode":"transductive"}. This record does not assert independent reproduction.

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