# Semantic Segmentation on ADE20K-C level 2 corruptions (val) Source: [Semantic Segmentation on ADE20K-C level 2 corruptions (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:10:54.524Z Evaluation of Semantic Segmentation performance on the ADE20K-C level 2 subset, focusing on robustness metrics across various image degradations (e.g., brightness, fog, JPEG compression, motion blur). 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) | ADE20K-C level 2 corruptions (val) | | Metric | mIoU (Brightness) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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 (Brightness)](): Higher is better; unit: PERCENT. - [mIoU (Contrast)](): Higher is better; unit: PERCENT. - [mIoU (Defocus)](): Higher is better; unit: PERCENT. - [mIoU (Elastic)](): Higher is better; unit: PERCENT. - [mIoU (Fog)](): Higher is better; unit: PERCENT. - [mIoU (Frost)](): Higher is better; unit: PERCENT. - [mIoU (Gaussian Noise)](): Higher is better; unit: PERCENT. - [mIoU (Glass Blur)](): Higher is better; unit: PERCENT. - [mIoU (Impulse Noise)](): Higher is better; unit: PERCENT. - [mIoU (JPEG Compression)](): Higher is better; unit: PERCENT. - [mIoU (Motion Blur)](): Higher is better; unit: PERCENT. - [mIoU (Pixelation)](): Higher is better; unit: PERCENT. - [mIoU (Shot Noise)](): Higher is better; unit: PERCENT. - [mIoU (Snow)](): Higher is better; unit: PERCENT. - [mIoU (Zoom Blur)](): Higher is better; unit: PERCENT. - [mIoU (Average)](): Higher is better; unit: PERCENT. ## Recorded results | Method | mIoU (Brightness) | Result date | Report paper | | --- | --- | --- | --- | | VICT | 47.8 | Not recorded | 68fa779d1e209131cea745cd | | VICT | 47.5 | Not recorded | 68fa779d1e209131cea745cd | | Painter | 47.1 | Not recorded | 68fa779d1e209131cea745cd | | Painter | 47.1 | Not recorded | 68fa779d1e209131cea745cd | ### VICT mIoU (Brightness): 47.8. Result ID: 699553463badfaffe643610a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"one-shot setting"}. This record does not assert independent reproduction. ### VICT mIoU (Brightness): 47.5. Result ID: 699553463badfaffe6436108. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"zero-shot setting"}. This record does not assert independent reproduction. ### Painter mIoU (Brightness): 47.1. Result ID: 699553463badfaffe6436107. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"zero-shot setting"}. This record does not assert independent reproduction. ### Painter mIoU (Brightness): 47.1. Result ID: 699553463badfaffe6436109. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"one-shot setting"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.