2021/12/07 by Edoardo Arnaudo, Arnaudo, Edoardo, Fabio Cermelli +7
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Multimodal Machine Learning Applications #cs.CV #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2112.03814
12 pages, ICIAP 2021
arxiv created 2021/12/07 · openalex publication_date 2021/12/07 · arxiv updated 2021/12/08 · openalex created_date 2021/12/31 · openalex updated_date 2026/07/28
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.