Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917599569248256 |
|---|---|
| author | Williams, David S. W. De Martini, Daniele Gadd, Matthew Newman, Paul |
| author_facet | Williams, David S. W. De Martini, Daniele Gadd, Matthew Newman, Paul |
| contents | Knowing when a trained segmentation model is encountering data that is different to its training data is important. Understanding and mitigating the effects of this play an important part in their application from a performance and assurance perspective - this being a safety concern in applications such as autonomous vehicles (AVs). This work presents a segmentation network that can detect errors caused by challenging test domains without any additional annotation in a single forward pass. As annotation costs limit the diversity of labelled datasets, we use easy-to-obtain, uncurated and unlabelled data to learn to perform uncertainty estimation by selectively enforcing consistency over data augmentation. To this end, a novel segmentation benchmark based on the SAX Dataset is used, which includes labelled test data spanning three autonomous-driving domains, ranging in appearance from dense urban to off-road. The proposed method, named Gamma-SSL, consistently outperforms uncertainty estimation and Out-of-Distribution (OoD) techniques on this difficult benchmark - by up to 10.7% in area under the receiver operating characteristic (ROC) curve and 19.2% in area under the precision-recall (PR) curve in the most challenging of the three scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17653 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data Williams, David S. W. De Martini, Daniele Gadd, Matthew Newman, Paul Computer Vision and Pattern Recognition Robotics Knowing when a trained segmentation model is encountering data that is different to its training data is important. Understanding and mitigating the effects of this play an important part in their application from a performance and assurance perspective - this being a safety concern in applications such as autonomous vehicles (AVs). This work presents a segmentation network that can detect errors caused by challenging test domains without any additional annotation in a single forward pass. As annotation costs limit the diversity of labelled datasets, we use easy-to-obtain, uncurated and unlabelled data to learn to perform uncertainty estimation by selectively enforcing consistency over data augmentation. To this end, a novel segmentation benchmark based on the SAX Dataset is used, which includes labelled test data spanning three autonomous-driving domains, ranging in appearance from dense urban to off-road. The proposed method, named Gamma-SSL, consistently outperforms uncertainty estimation and Out-of-Distribution (OoD) techniques on this difficult benchmark - by up to 10.7% in area under the receiver operating characteristic (ROC) curve and 19.2% in area under the precision-recall (PR) curve in the most challenging of the three scenarios. |
| title | Mitigating Distributional Shift in Semantic Segmentation via Uncertainty Estimation from Unlabelled Data |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2402.17653 |