# Glass-like Object Segmentation on Trans10k (test)

Source: [Glass-like Object Segmentation on Trans10k (test)](<https://www.sota2.com/research/sota/glass-like-object-segmentation-on-trans10k-test>)

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

Data updated: 2026-02-26T06:10:14.371Z

Evaluation of segmentation performance specifically targeting glass-like objects using the test split of the Trans10k dataset, reporting metrics such as mIoU, Accuracy, mAE, and mBER.

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 | Glass-like Object Segmentation |
| Dataset (including any stated split) | Trans10k (test) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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/glass-like-object-segmentation-on-trans10k-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/glass-like-object-segmentation-on-trans10k-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [mAE](<https://www.sota2.com/research/sota/glass-like-object-segmentation-on-trans10k-test.md?metric=mAE>): Lower is better; unit: SCALAR.

- [mBER](<https://www.sota2.com/research/sota/glass-like-object-segmentation-on-trans10k-test.md?metric=mBER>): Lower is better; unit: SCALAR.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| EBLNet | 90.28 | Not recorded | 68fa6b691e209131cea2e313 |
| EBLNet | 89.58 | Not recorded | 68fa6b691e209131cea2e313 |
| Translab | 87.63 | Not recorded | 68fa6b691e209131cea2e313 |
| Deeplabv3+ | 84.54 | Not recorded | 68fa6b691e209131cea2e313 |
| Deeplabv3+ | 84.26 | Not recorded | 68fa6b691e209131cea2e313 |
| PSPNet | 82.38 | Not recorded | 68fa6b691e209131cea2e313 |
| FCN | 79.67 | Not recorded | 68fa6b691e209131cea2e313 |
| DenseAspp | 78.11 | Not recorded | 68fa6b691e209131cea2e313 |
| Deeplabv3+ | 75.27 | Not recorded | 68fa6b691e209131cea2e313 |
| HRNet | 74.56 | Not recorded | 68fa6b691e209131cea2e313 |
| BiSeNet | 73.93 | Not recorded | 68fa6b691e209131cea2e313 |
| RefineNet | 66.03 | Not recorded | 68fa6b691e209131cea2e313 |

### EBLNet

mIoU: 90.28. Result ID: 698e89aaffc3901de09e78a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Implementation](<https://github.com/hehao13/EBLNet>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Output Stride (OS)":"8","Inference Scale":"single scale"}. This record does not assert independent reproduction.

### EBLNet

mIoU: 89.58. Result ID: 698e89aaffc3901de09e78a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Implementation](<https://github.com/hehao13/EBLNet>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Output Stride (OS)":"16","Inference Scale":"single scale"}. This record does not assert independent reproduction.

### Translab

mIoU: 87.63. Result ID: 698e89aaffc3901de09e78a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68141e209131cea1a0ad.md>)

[Implementation](<https://www.sota2.com/github.com/xieenze/Segment_Transparent_Objects>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Inference Scale":"single scale"}. This record does not assert independent reproduction.

### Deeplabv3+

mIoU: 84.54. Result ID: 698e89aaffc3901de09e789e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Inference Scale":"single scale"}. This record does not assert independent reproduction.

### Deeplabv3+

mIoU: 84.26. Result ID: 698e89aaffc3901de09e78a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

Recorded evaluation configuration: {"Backbone":"Xception65","Inference Scale":"single scale"}. This record does not assert independent reproduction.

### PSPNet

mIoU: 82.38. Result ID: 698e89aaffc3901de09e78a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634b1e209131ce9fdc7e.md>)

[Implementation](<https://github.com/hszhao/PSPNet>)

Recorded evaluation configuration: {"Inference Scale":"single scale"}. This record does not assert independent reproduction.

### FCN

mIoU: 79.67. Result ID: 698e89aaffc3901de09e789f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa627b1e209131ce9f9766.md>)

[Implementation](<http://fcn.berkeleyvision.org/>)

Recorded evaluation configuration: {"Inference Scale":"single scale"}. This record does not assert independent reproduction.

### DenseAspp

mIoU: 78.11. Result ID: 698e89aaffc3901de09e789d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

Recorded evaluation configuration: {"Inference Scale":"single scale"}. This record does not assert independent reproduction.

### Deeplabv3+

mIoU: 75.27. Result ID: 698e89aaffc3901de09e789a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

Recorded evaluation configuration: {"Backbone":"MobileNetv2","Inference Scale":"single scale"}. This record does not assert independent reproduction.

### HRNet

mIoU: 74.56. Result ID: 698e89aaffc3901de09e789b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67391e209131cea15032.md>)

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

Recorded evaluation configuration: {"Inference Scale":"single scale"}. This record does not assert independent reproduction.

### BiSeNet

mIoU: 73.93. Result ID: 698e89aaffc3901de09e789c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64aa1e209131cea05f98.md>)

Recorded evaluation configuration: {"Inference Scale":"single scale"}. This record does not assert independent reproduction.

### RefineNet

mIoU: 66.03. Result ID: 698e89aaffc3901de09e78a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b691e209131cea2e313.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63011e209131ce9fc44e.md>)

[Implementation](<https://github.com/guosheng/refinenet>)

Recorded evaluation configuration: {"Inference Scale":"single scale"}. This record does not assert independent reproduction.

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