Publikasjonsdetaljer
Arrangement: CVPR 2020 Workshop on AGRICULTURE-VISION (Seattle (Online))
Dato: 14. juni 2020 –19. juni 2020
År: 2020
Arrangør: CVPR and AGRICULTURE-VISION
Lenker:
PROSJEKT: github.com/samleoqh/MSCG-Net
FULLTEKST: drive.google.com/file/d/1zNRKn7OtlT3yIk42l12gEJqGE7gsSiKS/view
We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. Building on the recently proposed Self-Constructing Graph (SCG) module, which makes use of learnable latent variables to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs, we leverage multiple views in order to explicitly exploit the rotational invariance in airborne images. We further develop an adaptive class weighting loss to address the class imbalance. We demonstrate the effectiveness and flexibility of the proposed method on the Agriculture-Vision challenge dataset and our model achieves very competitive results
(0.547 mIoU) with much fewer parameters and at a lower
computational cost compared to related pure-CNN based
work.