Topology Maintained Structure Encoding
Deep learning has been used as a powerful tool for various tasks in computer vision, such as image segmentation, object recognition and data generation. A key part of end-to-end training is designing the appropriate encoder to extract specific features from the input data. However, few encoders maintain the topological properties of data, such as connection structures and global contours. In this paper, we introduce a Voronoi Diagram encoder based on convex set distance (CSVD) and apply it in edge encoding. The boundaries of Voronoi cells is related to detected edges of structures and contours. The CSVD model improves contour extraction in CNN and structure generation in GAN. We also show the experimental results and demonstrate that the proposed model has great potentiality in different visual problems where topology information should be involved.
Code (0)
등록된 구현이 없습니다.
Tasks
Image SegmentationObject RecognitionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Structure-Aware Lane Graph Transformer Model for Vehicle Trajectory Prediction
Accurate prediction of future trajectories for surrounding vehicles is vital for the safe operation of autonomous vehicles. This study proposes a Lane Graph Transformer (LGT) model with structure-aware capabilities. Its …
Autonomous VehiclesTrajectory PredictionSolution Space Topology Guides CMTS Search
A fundamental question in search-guided AI: what topology should guide Monte Carlo Tree Search (MCTS) in puzzle solving? Prior work applied topological features to guide MCTS in ARC-style tasks using grid topology -- the…
GeoReFormer: Geometry-Aware Refinement for Lane Segment Detection and Topology Reasoning
Accurate 3D lane segment detection and topology reasoning are critical for structured online map construction in autonomous driving. Recent transformer-based approaches formulate this task as query-based set prediction, …
Autonomous DrivingObject DetectionTopoImb: Toward Topology-level Imbalance in Learning from Graphs
Graph serves as a powerful tool for modeling data that has an underlying structure in non-Euclidean space, by encoding relations as edges and entities as nodes. Despite developments in learning from graph-structured data…
Autoencoding topology
The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoencoders) to fit deep neural networks. Fro…
BIG-bench Machine LearningClusteringDimensionality Reduction