Not logged in.
Quick Search - Contribution
Contribution Details
Type | Conference or Workshop Paper |
Scope | Discipline-based scholarship |
Published in Proceedings | Yes |
Title | Recurrent Vision Transformers for Object Detection with Event Cameras |
Organization Unit | |
Authors |
|
Presentation Type | paper |
Item Subtype | Original Work |
Refereed | Yes |
Status | Published in final form |
Language |
|
ISBN | 979-8-3503-0129-8 |
ISSN | 1063-6919 |
Page Range | 13884 - 13893 |
Event Title | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 |
Event Type | conference |
Event Location | Vancouver, BC, Canada |
Event Start Date | June 18 - 2023 |
Event End Date | June 22 - 2023 |
Series Name | IEEE Conference on Computer Vision and Pattern Recognition. Proceedings |
Publisher | Institute of Electrical and Electronics Engineers |
Abstract Text | We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. Event cameras provide visual information with submillisecond latency at a high-dynamic range and with strong robustness against motion blur. These unique properties offer great potential for low-latency object detection and tracking in time-critical scenarios. Prior work in event-based vision has achieved outstanding detection performance but at the cost of substantial inference time, typically beyond 40 milliseconds. By revisiting the high-level design of recurrent vision backbones, we reduce inference time by a factor of 6 while retaining similar performance. To achieve this, we explore a multi-stage design that utilizes three key concepts in each stage: first, a convolutional prior that can be regarded as a conditional positional embedding. Second, local and dilated global self-attention for spatial feature interaction. Third, recurrent temporal feature aggregation to minimize latency while retaining temporal information. RVTs can be trained from scratch to reach state-of-the-art performance on event-based object detection - achieving an mAP of 47.2% on the Gen1 automotive dataset. At the same time, RVTs offer fast inference (< 12 ms on a T4 GPU) and favorable parameter efficiency (5 × fewer than prior art). Our study brings new insights into effective design choices that can be fruitful for research beyond event-based vision. |
Digital Object Identifier | 10.1109/CVPR52729.2023.01334 |
PDF File | Download from ZORA |
Export |
BibTeX
EP3 XML (ZORA) |