Recurrent Vision Transformers for Object Detection with Event Cameras
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
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. Code: https://github.com/uzh-rpg/RVT
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01167 · Cited by 8,494
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., & Woo, W.-C. (2015) · arXiv · doi:10.48550/arxiv.1506.04214 · Cited by 7,709 · cited 2×
“By avoiding Conv-LSTM units [42], we can drastically reduce the computational complexity and parameter count.”
MethodYOLOX: Exceeding YOLO Series in 2021
Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021) · arXiv · doi:10.48550/arxiv.2107.08430 · Cited by 2,965
ViViT: A Video Vision Transformer
Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., & Schmid, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00676 · Cited by 2,767 · cited 2×
“Attention-based models have recently also been explored in video classification [1,5,13,48] where the models are applied directly to a set of frames.”
MethodGallego, G., Delbruck, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A. J., Conradt, J., Daniilidis, K., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3008413 · Cited by 2,566
Self-citationIs Space-Time Attention All You Need for Video Understanding?
Bertasius, G., Wang, H., & Torresani, L. (2021) · arXiv · doi:10.48550/arxiv.2102.05095 · Cited by 1,663
Going deeper with Image Transformers
Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., & Jegou, H. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00010 · Cited by 1,259 · cited 3×
“We found that LayerScale enables a wider range of learning rates.”
Method(2022) · doi:10.1007/978-3-031-20053-3_27 · Cited by 1,060
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., & Shen, C. (2021) · arXiv · doi:10.48550/arxiv.2104.13840 · Cited by 817
Conditional Positional Encodings for Vision Transformers
Chu, X., Tian, Z., Zhang, B., Wang, X., & Shen, C. (2021) · arXiv · doi:10.48550/arxiv.2102.10882 · Cited by 489 · cited 2×
“This convolution also endows our model with a conditional positional embedding [9] such that we do not require absolute [12, 52] or relative [32] positional embeddings.”
MethodResultMasked Autoencoders As Spatiotemporal Learners
Feichtenhofer, C., Fan, H., Li, Y., & He, K. (2022) · arXiv · doi:10.48550/arxiv.2205.09113 · Cited by 345
Metadata
- Authors
- Gehrig, M., & Scaramuzza, D.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 13884-13893
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386075690
- Cited by
- 206
- References
- 17
- FWCI
- 23.42
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.