3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection
| Autor: | Jingang Tan, Jianfeng Feng, Xiaolin Zhang, Lili Chen, Liang Du, Hongkai Wen, Jiamao Li, Xiangyang Xue |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Point cloud Feature selection 02 engineering and technology 010501 environmental sciences TS 01 natural sciences QA76 Computer Science - Robotics 0202 electrical engineering electronic engineering information engineering Segmentation 0105 earth and related environmental sciences business.industry Process (computing) 020206 networking & telecommunications Pattern recognition Euclidean distance Task (computing) TA Benchmark (computing) Embedding Artificial intelligence business Robotics (cs.RO) |
| Zdroj: | ICRA |
| ISSN: | 1050-4729 |
| Popis: | We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptively selects and fuses the reciprocal semantic and instance features from two tasks in a coupled manner. To further boost the performance of the instance segmentation task in our 3DCFS, we investigate a loss function that helps the model learn to balance the magnitudes of the output embedding dimensions during training, which makes calculating the Euclidean distance more reliable and enhances the generalizability of the model. Extensive experiments demonstrate that our 3DCFS outperforms state-of-the-art methods on benchmark datasets in terms of accuracy, speed and computational cost. Comment: icra 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|