MMDR: A Result Feature Fusion Object Detection Approach for Autonomous System
Not on the map. Why?
Abstract (arXiv)
Object detection has been extensively utilized in autonomous systems in recent years, encompassing both 2D and 3D object detection. Recent research in this field has primarily centered around multimodal approaches for addressing this issue.In this paper, a multimodal fusion approach based on result feature-level fusion is proposed. This method utilizes the outcome features generated from single modality sources, and fuses them for downstream tasks.Based on this method, a new post-fusing network is proposed for multimodal object detection, which leverages the single modality outcomes as features. The proposed approach, called Multi-Modal Detector based on Result features (MMDR), is designed to work for both 2D and 3D object detection tasks. Compared to previous multimodal models, the proposed approach in this paper performs feature fusion at a later stage, enabling better representation of the deep-level features of single modality sources. Additionally, the MMDR model incorporates shallow global features during the feature fusion stage, endowing the model with the ability to perceive background information and the overall input, thereby avoiding issues such as missed detections.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 36 references that are in the map. First posted on arXiv 19 Apr 2023.
Builds on
31 of 36 references.
References · 31
- 2017Attention Is All You Needcited by 59,932
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2020End-to-End Object Detection with Transformerscited by 7,384
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
- 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
- 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
- 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
- 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
- 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
19 more
- 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
- 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
- 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
- 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
- 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
- 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
- 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
- 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
- 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
- 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
- 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
- 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
- 20203D Object Detection with Pointformercited by 194
- 2020CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detectioncited by 147
- 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
- 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
- 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86
- 2022PP-YOLOE: An evolved version of YOLOcited by 75
- 2021PP-YOLOv2: A Practical Object Detectorcited by 30
Built on by
Not cited yet.