Bidirectional Graph Reasoning Network for Panoptic Segmentation

Wu, Yangxin; Zhang, Gengwei; Gao, Yongfeng; Deng, Xiajun; Gong, Ke; Liang, Xiaodan; Li, Lin

doi:10.1109/cvpr42600.2020.00910

Cited by 53 publications

(26 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [6] improved the panoptic segmentation quality with a bidirectional path between the semantic and instance segmentation branches. Wu et al [43] constructed modular graph structure to reason their relations. Inspired by [23], Fan et al [15] generalized the traditional symbol spotting problem and considered both countable things and uncountable stuff symbols as one recognition task.…”

Section: Related Workmentioning

confidence: 99%

GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings

Zheng¹,

Li²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Spotting graphical symbols from the computer-aided design (CAD) drawings is essential to many industrial applications. Different from raster images, CAD drawings are vector graphics consisting of geometric primitives such as segments, arcs, and circles. By treating each CAD drawing as a graph, we propose a novel graph attention network GAT-CADNet to solve the panoptic symbol spotting problem: vertex features derived from the GAT branch are mapped to semantic labels, while their attention scores are cascaded and mapped to instance prediction. Our key contributions are three-fold: 1) the instance symbol spotting task is formulated as a subgraph detection problem and solved by predicting the adjacency matrix; 2) a relative spatial encoding (RSE) module explicitly encodes the relative positional and geometric relation among vertices to enhance the vertex attention; 3) a cascaded edge encoding (CEE) module extracts vertex attentions from multiple stages of GAT and treats them as edge encoding to predict the adjacency matrix. The proposed GAT-CADNet is intuitive yet effective and manages to solve the panoptic symbol spotting problem in one consolidated network. Extensive experiments and ablation studies on the public benchmark show that our graph-based approach surpasses existing state-of-the-art methods by a large margin.

show abstract

Section: Related Workmentioning

confidence: 99%

GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings

Zheng¹,

Li²,

Zhu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Panoptic-DeepLab [2] builds on DeeperLab and introduces a dual-decoder structure to regress instance object centers and semantic labels, respectively. In contrast, some research works [23], [24] have also used graph-based approaches to provide panoptic segmentation results on images.…”

Section: A Image Panoptic Segmentationmentioning

confidence: 99%

SMAC-Seg: LiDAR Panoptic Segmentation via Sparse Multi-directional Attention Clustering

Li¹,

Razani²,

Xu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Panoptic segmentation aims to address semantic and instance segmentation simultaneously in a unified framework. However, an efficient solution of panoptic segmentation in applications like autonomous driving is still an open research problem. In this work, we propose a novel LiDAR-based panoptic system, called SMAC-Seg. We present a learnable sparse multi-directional attention clustering to segment multi-scale foreground instances. SMAC-Seg is a real-time clustering-based approach, which removes the complex proposal network to segment instances. Most existing clustering-based methods use the difference of the predicted and ground truth center offset as the only loss to supervise the instance centroid regression. However, this loss function only considers the centroid of the current object, but its relative position with respect to the neighbouring objects is not considered when learning to cluster. Thus, we propose to use a novel centroid-aware repel loss as an additional term to effectively supervise the network to differentiate each object cluster with its neighbours. Our experimental results show that SMAC-Seg achieves state-of-theart performance among all real-time deployable networks on both large-scale public SemanticKITTI and nuScenes panoptic segmentation datasets.

show abstract

“…Although several works combine semantic and instance segmentation for the task of panoptic segmentation [10,19,28,26,7], first described in [14], some works explicitly aim at mask improvement through the combination of the two tasks. The authors of [8] add an Atrous convolution segmentation head to Mask R-CNN to refine the predicted segmentation masks.…”

Section: Related Workmentioning

confidence: 99%

Anisotropic Diffusion-Based Enhancement of Scene Segmentation with Instance Labels

Kleitsiotis

Mariolis

Giakoumis

et al. 2021

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Bidirectional Graph Reasoning Network for Panoptic Segmentation

Cited by 53 publications

References 21 publications

GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings

GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings

SMAC-Seg: LiDAR Panoptic Segmentation via Sparse Multi-directional Attention Clustering

Anisotropic Diffusion-Based Enhancement of Scene Segmentation with Instance Labels

Contact Info

Product

Resources

About