A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images
Autor: | Edoardo Arnaudo, Fabio Cermelli, Antonio Tavera, Claudio Rossi, Barbara Caputo |
---|---|
Rok vydání: | 2022 |
Předmět: |
FOS: Computer and information sciences
incremental learning computer vision semantic segmentation aerial images incremental learning Computer Vision and Pattern Recognition (cs.CV) Image and Video Processing (eess.IV) FOS: Electrical engineering electronic engineering information engineering Computer Science - Computer Vision and Pattern Recognition aerial images Electrical Engineering and Systems Science - Image and Video Processing computer vision semantic segmentation |
Zdroj: | Image Analysis and Processing – ICIAP 2022 ISBN: 9783031064296 |
Popis: | 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. Code available at: https://github.com/edornd/contrastive-distillation. 12 pages, ICIAP 2021 |
Databáze: | OpenAIRE |
Externí odkaz: |