Multi-view Self-Constructing Graph Convolutional Networks with Adaptive Class Weighting Loss for Semantic Segmentation

2020-04-21 · Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

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. Code will be available at: github.com/samleoqh/MSCG-Net

📄 PDF Abstract BibTeX arXiv:2004.10327

Code (2)

samleoqh/MSCG-Net 공식 구현 pytorch

samleoqh/MultiModNet pytorch

Tasks

Knowledge Graphs Semantic Segmentation

Methods 이 논문이 사용한 방법론

Graph Convolutional Networks 설명 없음

SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation

2020-09-03 · Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

Capturing global contextual representations by exploiting long-range pixel-pixel dependencies has shown to improve semantic segmentation performance. However, how to do this efficiently is an open question as current app…

Graph Reconstruction Open-Ended Question Answering Segmentation Semantic Segmentation

Self-Constructing Graph Convolutional Networks for Semantic Labeling

2020-03-15 · Qinghui Liu, Michael Kampffmeyer, Robert Jenssen, Arnt-Børre Salberg

Graph Neural Networks (GNNs) have received increasing attention in many fields. However, due to the lack of prior graphs, their use for semantic labeling has been limited. Here, we propose a novel architecture called the…

Graph Reconstruction Knowledge Graphs

Contrastive Multi-view Subspace Clustering of Hyperspectral Images based on Graph Convolutional Networks

2023-12-11 · Renxiang Guan, Zihao Li, Xianju Li, Chang Tang 외

High-dimensional and complex spectral structures make the clustering of hyperspectral images (HSI) a challenging task. Subspace clustering is an effective approach for addressing this problem. However, current subspace c…

Clustering Contrastive Learning Multi-view Subspace Clustering

Squeeze and Excitation: A Weighted Graph Contrastive Learning for Collaborative Filtering

2025-04-06 · Zheyu Chen, Jinfeng Xu, Yutong Wei, Ziyue Peng

Contrastive Learning (CL) has recently emerged as a powerful technique in recommendation systems, particularly for its capability to harness self-supervised signals from perturbed views to mitigate the persistent challen…

Collaborative Filtering Contrastive Learning Recommendation Systems Representation Learning

FedMSGL: A Self-Expressive Hypergraph Based Federated Multi-View Learning

2025-03-12 · Daoyuan Li, Zuyuan Yang, Shengli Xie

Federated learning is essential for enabling collaborative model training across decentralized data sources while preserving data privacy and security. This approach mitigates the risks associated with centralized data c…

Federated Learning MULTI-VIEW LEARNING