# IC Metal Line Segmentation on ICs 1-7 In-distribution (test)

Source: [IC Metal Line Segmentation on ICs 1-7 In-distribution (test)](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test>)

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

Data updated: 2026-03-18T08:54:10.201Z

Evaluation of IC Metal Line Segmentation performance on the ICs 1-7 In-distribution test set, utilizing specialized metrics such as ESD measurements (total, opens, shorts), Pixel Accuracy (PA), Dice coefficient, and IoU.

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 | IC Metal Line Segmentation |
| Dataset (including any stated split) | ICs 1-7 In-distribution (test) |
| Metric | ESD Total |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 9 of 9 |
| 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

- [ESD Total](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=ESD%20Total>): Lower is better; unit: SCALAR.

- [ESD Error Rate (%)](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=ESD%20Error%20Rate%20(%25)>): Lower is better; unit: PERCENT.

- [ESD Opens](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=ESD%20Opens>): Lower is better; unit: SCALAR.

- [ESD Shorts](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=ESD%20Shorts>): Lower is better; unit: SCALAR.

- [ESD FPs](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=ESD%20FPs>): Lower is better; unit: SCALAR.

- [ESD FNs](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=ESD%20FNs>): Lower is better; unit: SCALAR.

- [Pixel Accuracy (PA)](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=Pixel%20Accuracy%20(PA)>): Higher is better; unit: PERCENT.

- [Dice Coefficient](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=Dice%20Coefficient>): Higher is better; unit: PERCENT.

- [IoU](<https://www.sota2.com/research/sota/ic-metal-line-segmentation-on-ics-1-7-in-distribution-test.md?metric=IoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ESD Total | Result date | Report paper |
| --- | --- | --- | --- |
| SAMSEM | 263 | Not recorded | 69ba318e0636e5bf4afc085b |
| SAMSEM | 286 | Not recorded | 69ba318e0636e5bf4afc085b |
| SAMSEM | 289 | Not recorded | 69ba318e0636e5bf4afc085b |
| SAMSEM | 323 | Not recorded | 69ba318e0636e5bf4afc085b |
| U-Net | 1618 | Not recorded | 69ba318e0636e5bf4afc085b |
| SAMSEM | 1914 | Not recorded | 69ba318e0636e5bf4afc085b |
| FCN | 2067 | Not recorded | 69ba318e0636e5bf4afc085b |
| SAMIC | 2178 | Not recorded | 69ba318e0636e5bf4afc085b |
| DeepLabV3 | 2187 | Not recorded | 69ba318e0636e5bf4afc085b |

### SAMSEM

ESD Total: 263. Result ID: 69ba683147f34ce924a475b9.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

Recorded evaluation configuration: {"approach":"multi-scale (Model 1 + Model 2)"}. This record does not assert independent reproduction.

### SAMSEM

ESD Total: 286. Result ID: 69ba683147f34ce924a475bd.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

Recorded evaluation configuration: {"model":"only 2","input\_resolution":"512x512 patches"}. This record does not assert independent reproduction.

### SAMSEM

ESD Total: 289. Result ID: 69ba683147f34ce924a475bb.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

Recorded evaluation configuration: {"model\_config":"single model"}. This record does not assert independent reproduction.

### SAMSEM

ESD Total: 323. Result ID: 69ba683147f34ce924a475ba.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

Recorded evaluation configuration: {"loss":"only pixel loss"}. This record does not assert independent reproduction.

### U-Net

ESD Total: 1618. Result ID: 69ba683147f34ce924a475bf.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

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

### SAMSEM

ESD Total: 1914. Result ID: 69ba683147f34ce924a475bc.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

Recorded evaluation configuration: {"model":"only 1","input\_resolution":"original-size"}. This record does not assert independent reproduction.

### FCN

ESD Total: 2067. Result ID: 69ba683147f34ce924a475c1.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

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

### SAMIC

ESD Total: 2178. Result ID: 69ba683147f34ce924a475be.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.md>)

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

### DeepLabV3

ESD Total: 2187. Result ID: 69ba683147f34ce924a475c0.

[Reporting paper](<https://www.sota2.com/research/paper/69ba318e0636e5bf4afc085b.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.
