Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912176096149504 |
|---|---|
| author | Thakur, Rini Smita Kurmi, Vinod K. |
| author_facet | Thakur, Rini Smita Kurmi, Vinod K. |
| contents | Semi-supervised (SS) semantic segmentation exploits both labeled and unlabeled images to overcome tedious and costly pixel-level annotation problems. Pseudolabel supervision is one of the core approaches of training networks with both pseudo labels and ground-truth labels. This work uses aleatoric or data uncertainty and energy based modeling in intersection-union pseudo supervised network.The aleatoric uncertainty is modeling the inherent noise variations of the data in a network with two predictive branches. The per-pixel variance parameter obtained from the network gives a quantitative idea about the data uncertainty. Moreover, energy-based loss realizes the potential of generative modeling on the downstream SS segmentation task. The aleatoric and energy loss are applied in conjunction with pseudo-intersection labels, pseudo-union labels, and ground-truth on the respective network branch. The comparative analysis with state-of-the-art methods has shown improvement in performance metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01640 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentation Thakur, Rini Smita Kurmi, Vinod K. Computer Vision and Pattern Recognition Semi-supervised (SS) semantic segmentation exploits both labeled and unlabeled images to overcome tedious and costly pixel-level annotation problems. Pseudolabel supervision is one of the core approaches of training networks with both pseudo labels and ground-truth labels. This work uses aleatoric or data uncertainty and energy based modeling in intersection-union pseudo supervised network.The aleatoric uncertainty is modeling the inherent noise variations of the data in a network with two predictive branches. The per-pixel variance parameter obtained from the network gives a quantitative idea about the data uncertainty. Moreover, energy-based loss realizes the potential of generative modeling on the downstream SS segmentation task. The aleatoric and energy loss are applied in conjunction with pseudo-intersection labels, pseudo-union labels, and ground-truth on the respective network branch. The comparative analysis with state-of-the-art methods has shown improvement in performance metrics. |
| title | Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.01640 |