Conference
A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images
| العنوان: | A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images |
|---|---|
| المؤلفون: | Arnaudo,Edoardo, Cermelli,Fabio, Tavera,Antonio, Rossi,Claudio, Caputo,Barbara |
| المساهمون: | Arnaudo, Edoardo, Cermelli, Fabio, Tavera, Antonio, Rossi, Claudio, Caputo, Barbara |
| بيانات النشر: | Springer CHE |
| سنة النشر: | 2022 |
| المجموعة: | PORTO@iris (Publications Open Repository TOrino - Politecnico di Torino) |
| مصطلحات موضوعية: | computer vision, semantic segmentation, aerial images, incremental learning |
| الوصف: | Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets. A major issue concerning current deep neural architectures is known as catastrophic forgetting, namely the inability to faithfully maintain past knowledge once a new set of data is provided for retraining. Over the years, several techniques have been proposed to mitigate this problem for image classification and object detection. However, only recently the focus has shifted towards more complex downstream tasks such as instance or semantic segmentation. Starting from incremental-class learning for semantic segmentation tasks, our goal is to adapt this strategy to the aerial domain, exploiting a peculiar feature that differentiates it from natural images, namely the orientation. In addition to the standard knowledge distillation approach, we propose a contrastive regularization, where any given input is compared with its augmented version (i.e. flipping and rotations) in order to minimize the difference between the segmentation features produced by both inputs. We show the effectiveness of our solution on the Potsdam dataset, outperforming the incremental baseline in every test. |
| نوع الوثيقة: | conference object |
| وصف الملف: | ELETTRONICO |
| اللغة: | English |
| Relation: | info:eu-repo/semantics/altIdentifier/wos/WOS:000870296100062; ispartofbook:Image Analysis and Processing – ICIAP 2021; International Conference on Image Analysis and Processing; firstpage:742; lastpage:754; numberofpages:13; info:eu-repo/grantAgreement/EC/H2020/corda__h2020::4a4635b3c497b2ff97bac8cf3393c315; http://hdl.handle.net/11583/2962571; info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85130960996; https://link.springer.com/chapter/10.1007/978-3-031-06430-2_62#Abs1 |
| DOI: | 10.1007/978-3-031-06430-2_62 |
| DOI: | 10.1007/978-3-031-06430-2_62#Abs1 |
| الاتاحة: | http://hdl.handle.net/11583/2962571 https://doi.org/10.1007/978-3-031-06430-2_62 https://link.springer.com/chapter/10.1007/978-3-031-06430-2_62#Abs1 |
| Rights: | info:eu-repo/semantics/openAccess |
| رقم الانضمام: | edsbas.177B8317 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1007/978-3-031-06430-2_62 |
|---|