Attention-based Proposals Refinement for 3D Object Detection
| Autor: | Minh-Quan Dao, Elwan Hery, Vincent Fremont |
|---|---|
| Přispěvatelé: | École Centrale de Nantes (Nantes Univ - ECN), Nantes Université (Nantes Univ), Autonomie des Robots et Maîtrise des interactions avec l’ENvironnement (LS2N - équipe ARMEN), Laboratoire des Sciences du Numérique de Nantes (LS2N), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-École Centrale de Nantes (Nantes Univ - ECN), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), ANR-20-THIA-0011,AIby4,AI by / for Human, Health and Industry(2020) |
| Jazyk: | angličtina |
| Rok vydání: | 2022 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Robotics Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO] [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Robotics (cs.RO) [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
| Zdroj: | 2022 IEEE Intelligent Vehicles Symposium (IV) 2022 IEEE Intelligent Vehicles Symposium (IV), Jun 2022, Aachen, Germany. pp.197-205, ⟨10.1109/IV51971.2022.9827019⟩ |
| DOI: | 10.1109/IV51971.2022.9827019⟩ |
| Popis: | Recent advances in 3D object detection are made by developing the refinement stage for voxel-based Region Proposal Networks (RPN) to better strike the balance between accuracy and efficiency. A popular approach among state-of-the-art frameworks is to divide proposals, or Regions of Interest (ROI), into grids and extract features for each grid location before synthesizing them to form ROI features. While achieving impressive performances, such an approach involves several hand-crafted components (e.g. grid sampling, set abstraction) which requires expert knowledge to be tuned correctly. This paper proposes a data-driven approach to ROI feature computing named APRO3D-Net which consists of a voxel-based RPN and a refinement stage made of Vector Attention. Unlike the original multi-head attention, Vector Attention assigns different weights to different channels within a point feature, thus being able to capture a more sophisticated relation between pooled points and ROI. Our method achieves a competitive performance of 84.85 AP for class Car at moderate difficulty on the validation set of KITTI and 47.03 mAP (average over 10 classes) on NuScenes while having the least parameters compared to closely related methods and attaining an inference speed at 15 FPS on NVIDIA V100 GPU. The code is released at https://github.com/quan-dao/APRO3D-Net. Accepted for IV 2022 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|