Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912992621232128 |
|---|---|
| author | Guarino, Vanessa Emanuela Winklmayr, Claudia Franzen, Jannik Rumberger, Josef Lorenz Pfeuffer, Manuel Greven, Sonja Maier-Hein, Klaus Lüth, Carsten T. Karg, Christoph Kainmueller, Dagmar |
| author_facet | Guarino, Vanessa Emanuela Winklmayr, Claudia Franzen, Jannik Rumberger, Josef Lorenz Pfeuffer, Manuel Greven, Sonja Maier-Hein, Klaus Lüth, Carsten T. Karg, Christoph Kainmueller, Dagmar |
| contents | Uncertainty Quantification (UQ) is crucial for ensuring the reliability of automated image segmentations in safety-critical domains like biomedical image analysis or autonomous driving. In segmentation, UQ generates pixel-wise uncertainty scores that must be aggregated into image-level scores for downstream tasks like Out-of-Distribution (OoD) or failure detection. Despite routine use of aggregation strategies, their properties and impact on downstream task performance have not yet been comprehensively studied. Global Average is the default choice, yet it does not account for spatial and structural features of segmentation uncertainty. Alternatives like patch-, class- and threshold-based strategies exist, but lack systematic comparison, leading to inconsistent reporting and unclear best practices. We address this gap by (1) formally analyzing properties, limitations, and pitfalls of common strategies; (2) proposing novel strategies that incorporate spatial uncertainty structure and (3) benchmarking their performance on OoD and failure detection across ten datasets that vary in image geometry and structure. We find that aggregators leveraging spatial structure yield stronger performance in both downstream tasks studied. However, the performance of individual aggregators depends heavily on dataset characteristics, so we (4) propose a meta-aggregator that integrates multiple aggregators and performs robustly across datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29941 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance Guarino, Vanessa Emanuela Winklmayr, Claudia Franzen, Jannik Rumberger, Josef Lorenz Pfeuffer, Manuel Greven, Sonja Maier-Hein, Klaus Lüth, Carsten T. Karg, Christoph Kainmueller, Dagmar Computer Vision and Pattern Recognition Machine Learning Uncertainty Quantification (UQ) is crucial for ensuring the reliability of automated image segmentations in safety-critical domains like biomedical image analysis or autonomous driving. In segmentation, UQ generates pixel-wise uncertainty scores that must be aggregated into image-level scores for downstream tasks like Out-of-Distribution (OoD) or failure detection. Despite routine use of aggregation strategies, their properties and impact on downstream task performance have not yet been comprehensively studied. Global Average is the default choice, yet it does not account for spatial and structural features of segmentation uncertainty. Alternatives like patch-, class- and threshold-based strategies exist, but lack systematic comparison, leading to inconsistent reporting and unclear best practices. We address this gap by (1) formally analyzing properties, limitations, and pitfalls of common strategies; (2) proposing novel strategies that incorporate spatial uncertainty structure and (3) benchmarking their performance on OoD and failure detection across ten datasets that vary in image geometry and structure. We find that aggregators leveraging spatial structure yield stronger performance in both downstream tasks studied. However, the performance of individual aggregators depends heavily on dataset characteristics, so we (4) propose a meta-aggregator that integrates multiple aggregators and performs robustly across datasets. |
| title | Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2603.29941 |