Improving Indoor Semantic Segmentation with Boundary-level Objectives
| Autor: | Roberto Amoroso, Lorenzo Baraldi, Rita Cucchiara |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Computer science
business.industry media_common.quotation_subject Boundary losses Boundary (topology) Geometric distance Robotics Machine learning computer.software_genre Task (project management) Indoor scene understanding Segmentation Boundary losses Segmentation Indoor scene understanding Augmented reality Quality (business) Artificial intelligence business Image retrieval computer media_common |
| Zdroj: | Advances in Computational Intelligence ISBN: 9783030850982 IWANN (2) |
| Popis: | While most of the recent literature on semantic segmentation has focused on outdoor scenarios, the generation of accurate indoor segmentation maps has been partially under-investigated, although being a relevant task with applications in augmented reality, image retrieval, and personalized robotics. With the goal of increasing the accuracy of semantic segmentation in indoor scenarios, we develop and propose two novel boundary-level training objectives, which foster the generation of accurate boundaries between different semantic classes. In particular, we take inspiration from the Boundary and Active Boundary losses, two recent proposals which deal with the prediction of semantic boundaries, and propose modified geometric distance functions that improve predictions at the boundary level. Through experiments on the NYUDv2 dataset, we assess the appropriateness of our proposal in terms of accuracy and quality of boundary prediction and demonstrate its accuracy gain. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|