MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Multi-task learning is commonly used in autonomous driving for solving various visual perception tasks. It offers significant benefits in terms of both performance and computational complexity. Current work on multi-task learning networks focus on processing a single input image and there is no known implementation of multi-task learning handling a sequence of images. In this work, we propose a multi-stream multi-task network to take advantage of using feature representations from preceding frames in a video sequence for joint learning of segmentation, depth, and motion. The weights of the current and previous encoder are shared so that features computed in the previous frame can be leveraged without additional computation. In addition, we propose to use the geometric mean of task losses as a better alternative to the weighted average of task losses. The proposed loss function facilitates better handling of the difference in convergence rates of different tasks. Experimental results on KITTI, Cityscapes and SYNTHIA datasets demonstrate that the proposed strategies outperform various existing multi-task learning solutions.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Vision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 9×
“KITTI [12] and Cityscapes [6] provide segmentation labels for 20 categories while SYNTHIA [39] dataset provides segmentation labels for 13 categories.”
BackgroundMethodInfluentialConvolutional 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 1×
“Convolution-LSTMs (Conv-LSTMs) [58, 53] and 3D convolutions [18] are other options.”
BackgroundCaruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636
Large-Scale Video Classification with Convolutional Neural Networks
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.223 · Cited by 6,354 · cited 2×
“[19] combine features from inputs separated by 15 frames in a video for classification.”
BackgroundMethod3D Convolutional Neural Networks for Human Action Recognition
Ji, S., Xu, W., Yang, M., & Yu, K. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.59 · Cited by 6,235
Ros, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.352 · Cited by 2,338
Long-Term Recurrent Convolutional Networks for Visual Recognition and Description
Donahue, J., Hendricks, L. A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2599174 · Cited by 1,547
Cited by
Liu, J., Liu, Z., Wu, G., Ma, L., Liu, R., Zhong, W., Luo, Z., & Fan, X. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00745 · Cited by 316
Deep Gait Recognition: A Survey
Sepas-Moghaddam, A., & Etemad, A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3151865 · Cited by 307
OmniDet: Surround View Cameras Based Multi-Task Visual Perception Network for Autonomous Driving
Ravi Kumar, V., Yogamani, S., Rashed, H., Sitsu, G., Witt, C., Leang, I., Milz, S., & Mader, P. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062324 · Cited by 121
“We evaluate the uncertainty loss from Kendall [23], the gradient magnitude normalization GradNorm [24], the dynamic task prioritization DTP [25], the dynamic weight average DWA [26] and the geometric loss [27].”
MethodSelf-citationFisheyeMODNet: Moving Object Detection on Surround-view Cameras for Autonomous Driving
Yahiaoui, M. (2019) · TU Dublin · doi:10.21427/v1ar-t994 · Cited by 41
Das, A., Krizek, P., Sistu, G., Burger, F., Madasamy, S., Uricar, M., Kumar, V. R., & Yogamani, S. (2020) · 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294677 · Cited by 25
“We use a multitask strategy where we leverage existing encoder and build a light decoder motivated by [26] [27].”
MethodSelf-citation
Metadata
- Authors
- Chennupati, S., Sistu, G., Yogamani, S., & Rawashdeh, S. A.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 1200-1210
- OpenAlex
- W2938544580
- Cited by
- 86
- References
- 14
- FWCI
- 3.54
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning. https://app.cochat.ai/papers/10.1109/cvprw.2019.00159
- The paper
- Chennupati, S., Sistu, G., Yogamani, S., & Rawashdeh, S. A. (2019). MultiNet++: Multi-Stream Feature Aggregation and Geometric Loss Strategy for Multi-Task Learning. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). https://doi.org/10.1109/cvprw.2019.00159
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.