Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification
Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possible errors due to missing local geometric context in the depth channel. This work proposes a novel Residual Attention Graph Convolutional Network that exploits the intrinsic geometric context inside a 3D space without using any kind of point features, allowing the use of organized or unorganized 3D data. Experiments are done in NYU Depth v1 and SUN-RGBD datasets to study the different configurations and to demonstrate the effectiveness of the proposed method. Experimental results show that the proposed method outperforms current state-of-the-art in geometric 3D scene classification tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationScene ClassificationSimilar Papers 제목 키워드 기반
Residual Graph Convolutional Network for Bird's-Eye-View Semantic Segmentation
Retrieving spatial information and understanding the semantic information of the surroundings are important for Bird's-Eye-View (BEV) semantic segmentation. In the application of autonomous driving, autonomous vehicles n…
Autonomous DrivingAutonomous VehiclesBird's-Eye View Semantic SegmentationData Augmentation+2Dual ResGCN for Balanced Scene GraphGeneration
Visual scene graph generation is a challenging task. Previous works have achieved great progress, but most of them do not explicitly consider the class imbalance issue in scene graph generation. Models learned without co…
Graph GenerationRelationScene Graph GenerationSelf-Attention Graph Residual Convolutional Networks for Event Detection with dependency relations
Event detection (ED) task aims to classify events by identifying key event trigger words embedded in a piece of text. Previous research have proved the validity of fusing syntactic dependency relations into Graph Convolu…
Event DetectionSentenceScattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
Graph convolutional networks (GCNs) have shown promising results in processing graph data by extracting structure-aware features. This gave rise to extensive work in geometric deep learning, focusing on designing network…
Graph AttentionNode ClassificationPoint-GR: Graph Residual Point Cloud Network for 3D Object Classification and Segmentation
In recent years, the challenge of 3D shape analysis within point cloud data has gathered significant attention in computer vision. Addressing the complexities of effective 3D information representation and meaningful fea…
3D Object ClassificationClassificationScene SegmentationSegmentation