# 3D Semantic Segmentation on nuScenes-C full fine-tuning Source: [3D Semantic Segmentation on nuScenes-C full fine-tuning]() Collection index: [llms.txt]() Data updated: 2026-06-19T08:27:15.159Z Evaluation of 3D Semantic Segmentation performance on the nuScenes-C dataset under full fine-tuning conditions, reporting metrics across various common corruptions (Fog, Rain, Snow, etc.) and mean performance. 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 | 3D Semantic Segmentation | | Dataset (including any stated split) | nuScenes-C full fine-tuning | | Metric | mCE | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 10 of 10 | | 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 - [mCE](): Lower is better; unit: SCALAR. - [mRR](): Higher is better; unit: PERCENT. - [mIoU (Fog)](): Higher is better; unit: PERCENT. - [mIoU (Rain)](): Higher is better; unit: PERCENT. - [mIoU (Snow)](): Higher is better; unit: PERCENT. - [mIoU (Blur)](): Higher is better; unit: PERCENT. - [mIoU (Beam)](): Higher is better; unit: PERCENT. - [mIoU (Cross)](): Higher is better; unit: PERCENT. - [mIoU (Echo)](): Higher is better; unit: PERCENT. - [mIoU (Sensor)](): Higher is better; unit: PERCENT. - [mIoU (Mean)](): Higher is better; unit: PERCENT. ## Recorded results | Method | mCE | Result date | Report paper | | --- | --- | --- | --- | | HilDA | 85.08 | Not recorded | 6a34cd13206542251d7c5ef7 | | LiMoE | 88.43 | Not recorded | 6a34cd13206542251d7c5ef7 | | HilDA† | 90.05 | Not recorded | 6a34cd13206542251d7c5ef7 | | CleverDistiller | 91.28 | Not recorded | 6a34cd13206542251d7c5ef7 | | LiMA | 91.43 | Not recorded | 6a34cd13206542251d7c5ef7 | | SuperFlow | 91.67 | Not recorded | 6a34cd13206542251d7c5ef7 | | Seal | 92.63 | Not recorded | 6a34cd13206542251d7c5ef7 | | Scalr | 99.86 | Not recorded | 6a34cd13206542251d7c5ef7 | | SLidR | 106.08 | Not recorded | 6a34cd13206542251d7c5ef7 | | Random | 112.2 | Not recorded | 6a34cd13206542251d7c5ef7 | ### HilDA mCE: 85.08. Result ID: 6a34fd5cfbc373592c325901. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. ### LiMoE mCE: 88.43. Result ID: 6a34fd5cfbc373592c3258fd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. ### HilDA† mCE: 90.05. Result ID: 6a34fd5cfbc373592c325900. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%","ablation":"without future BEV occupancy diffusion"}. This record does not assert independent reproduction. ### CleverDistiller mCE: 91.28. Result ID: 6a34fd5cfbc373592c3258fe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. ### LiMA mCE: 91.43. Result ID: 6a34fd5cfbc373592c3258ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. ### SuperFlow mCE: 91.67. Result ID: 6a34fd5cfbc373592c3258fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. ### Seal mCE: 92.63. Result ID: 6a34fd5cfbc373592c3258fa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. ### Scalr mCE: 99.86. Result ID: 6a34fd5cfbc373592c3258fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. ### SLidR mCE: 106.08. Result ID: 6a34fd5cfbc373592c3258f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. ### Random mCE: 112.2. Result ID: 6a34fd5cfbc373592c3258f8. [Reporting paper]() Recorded evaluation configuration: {"training\_mode":"full fine-tuning","labeled\_data":"100%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.