Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity
원문 초록
We propose a simple yet effective proposal-free architecture for lidar panoptic segmentation. We jointly optimize both semantic segmentation and class-agnostic instance classification in a single network using a pillar-based bird's-eye view representation. The instance classification head learns pairwise affinity between pillars to determine whether the pillars belong to the same instance or not. We further propose a local clustering algorithm to propagate instance ids by merging semantic segmentation and affinity predictions. Our experiments on nuScenes dataset show that our approach outperforms previous proposal-free methods and is comparable to proposal-based methods which requires extra annotation from object detection.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Cross-Domain Few-Shot Semantic Segmentation
SONNET: A Self-Guided Ordinal Regression Neural Network for Segmentation and Classification of Nuclei in Large-Scale Multi-Tissue Histology Images
Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature Fusion
Automatic Traffic Sign Detection and Recognition Using SegU-Net and a Modified Tversky Loss Function With L1-Constraint
Image Segmentation Based on Watershed and Edge Detection Techniques
Solving non-uniqueness in agglomerative hierarchical clustering using multidendrograms
토론
이 논문과 연결된 포럼 글이 아직 없습니다.