# Semantic Segmentation on ARIS Source: [Semantic Segmentation on ARIS]() Collection index: [llms.txt]() Data updated: 2026-03-10T10:05:52.214Z Evaluation of Semantic Segmentation performance on the ARIS dataset, reporting Precision and Recall metrics categorized by specific ice types (anchor ice, frazil ice, ice+water). 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) | ARIS | | Metric | Recall (anchor ice) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Recall (anchor ice)](): Higher is better; unit: PERCENT. - [Recall (frazil ice)](): Higher is better; unit: PERCENT. - [Recall (ice+water)](): Higher is better; unit: PERCENT. - [Recall (ice+water (fw))](): Higher is better; unit: PERCENT. - [Precision (anchor ice)](): Higher is better; unit: PERCENT. - [Precision (frazil ice)](): Higher is better; unit: PERCENT. - [Precision (ice+water)](): Higher is better; unit: PERCENT. - [Precision (ice+water (fw))](): Higher is better; unit: PERCENT. ## Recorded results | Method | Recall (anchor ice) | Result date | Report paper | | --- | --- | --- | --- | | P2S-SEG | 82.7 | Not recorded | 699fd3712d603e6de3e3be24 | | SegNet | 82.31 | Not recorded | 699fd3712d603e6de3e3be24 | | DenseNet | 76.96 | Not recorded | 699fd3712d603e6de3e3be24 | | Deeplab | 74.46 | Not recorded | 699fd3712d603e6de3e3be24 | | UNet | 73.75 | Not recorded | 699fd3712d603e6de3e3be24 | | SVM | 61.54 | Not recorded | 699fd3712d603e6de3e3be24 | ### P2S-SEG Recall (anchor ice): 82.7. Result ID: 69afecf56dbb7075b958d52c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SegNet Recall (anchor ice): 82.31. Result ID: 69afecf56dbb7075b958d52b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DenseNet Recall (anchor ice): 76.96. Result ID: 69afecf56dbb7075b958d52a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Deeplab Recall (anchor ice): 74.46. Result ID: 69afecf56dbb7075b958d528. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### UNet Recall (anchor ice): 73.75. Result ID: 69afecf56dbb7075b958d529. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SVM Recall (anchor ice): 61.54. Result ID: 69afecf56dbb7075b958d527. [Reporting paper]() [Method origin paper]() 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.