VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913581861175296 |
|---|---|
| author | Huang, Chengjie Abdelzad, Vahdat Sedwards, Sean Czarnecki, Krzysztof |
| author_facet | Huang, Chengjie Abdelzad, Vahdat Sedwards, Sean Czarnecki, Krzysztof |
| contents | Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects responding differently to the number of aggregated frames. To address this limitation, we propose an efficient adaptive method, which we call Variable Aggregation Detection (VADet). Instead of aggregating the entire scene using a fixed number of frames, VADet performs aggregation per object, with the number of frames determined by an object's observed properties, such as speed and point density. VADet thus reduces the inherent trade-offs of fixed aggregation and is not architecture specific. To demonstrate its benefits, we apply VADet to three popular single-stage detectors and achieve state-of-the-art performance on the Waymo dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13186 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregation Huang, Chengjie Abdelzad, Vahdat Sedwards, Sean Czarnecki, Krzysztof Computer Vision and Pattern Recognition Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects responding differently to the number of aggregated frames. To address this limitation, we propose an efficient adaptive method, which we call Variable Aggregation Detection (VADet). Instead of aggregating the entire scene using a fixed number of frames, VADet performs aggregation per object, with the number of frames determined by an object's observed properties, such as speed and point density. VADet thus reduces the inherent trade-offs of fixed aggregation and is not architecture specific. To demonstrate its benefits, we apply VADet to three popular single-stage detectors and achieve state-of-the-art performance on the Waymo dataset. |
| title | VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.13186 |