# Audio-Visual Semantic Segmentation on AVS-Semantic

Source: [Audio-Visual Semantic Segmentation on AVS-Semantic](<https://www.sota2.com/research/sota/audio-visual-semantic-segmentation-on-avs-semantic>)

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

Data updated: 2026-02-26T06:10:27.475Z

Evaluation of Audio-Visual Semantic Segmentation performance using the AVS-Semantic dataset, reporting metrics such as mIoU.

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 | Audio-Visual Semantic Segmentation |
| Dataset (including any stated split) | AVS-Semantic |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

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

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| QDFormer | 53.4 | Not recorded | 68fa72ed1e209131cea594b7 |
| QDFormer | 46.6 | Not recorded | 68fa72ed1e209131cea594b7 |
| AVS | 29.8 | Not recorded | 68fa72ed1e209131cea594b7 |
| AOT | 25.4 | Not recorded | 68fa72ed1e209131cea594b7 |
| AVSegFormer | 24.9 | Not recorded | 68fa72ed1e209131cea594b7 |
| AVS | 20.2 | Not recorded | 68fa72ed1e209131cea594b7 |
| 3DC | 17.3 | Not recorded | 68fa72ed1e209131cea594b7 |

### QDFormer

mIoU: 53.4. Result ID: 6992a2eb3a6c314849104f17.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Implementation](<https://github.com/lxa9867/QSD>)

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

### QDFormer

mIoU: 46.6. Result ID: 6992a2eb3a6c314849104f15.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Implementation](<https://github.com/lxa9867/QSD>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### AVS

mIoU: 29.8. Result ID: 6992a2eb3a6c314849104f16.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e711e209131cea3fcef.md>)

Recorded evaluation configuration: {"Backbone":"PVT-v2-Base"}. This record does not assert independent reproduction.

### AOT

mIoU: 25.4. Result ID: 6992a2eb3a6c314849104f12.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2d1e209131cea2c9e6.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### AVSegFormer

mIoU: 24.9. Result ID: 6992a2eb3a6c314849104f14.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71791e209131cea5174e.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### AVS

mIoU: 20.2. Result ID: 6992a2eb3a6c314849104f13.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e711e209131cea3fcef.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### 3DC

mIoU: 17.3. Result ID: 6992a2eb3a6c314849104f11.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72ed1e209131cea594b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70731e209131cea4b177.md>)

[Implementation](<https://github.com/sabarim/3DC-Seg>)

Recorded evaluation configuration: {"Backbone":"3DC"}. This record does not assert independent reproduction.

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