Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single model to perform multiple tasks at once (in this work, we consider depth estimation and semantic segmentation crucial for acquiring geometric and semantic understanding of the scene), while ii) doing it in real-time, and iii) using asymmetric datasets with uneven numbers of annotations per each modality. To overcome the first two issues, we adapt a recently proposed real-time semantic segmentation network, making changes to further reduce the number of floating point operations. To approach the third issue, we embrace a simple solution based on hard knowledge distillation under the assumption of having access to a powerful `teacher' network. We showcase how our system can be easily extended to handle more tasks, and more datasets, all at once, performing depth estimation and segmentation both indoors and outdoors with a single model. Quantitatively, we achieve results equivalent to (or better than) current state-of-the-art approaches with one forward pass costing just 13ms and 6.5 GFLOPs on 640×480 inputs. This efficiency allows us to directly incorporate the raw predictions of our network into the SemanticFusion framework [1] for dense 3D semantic reconstruction of the scene.
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 1×
“Due to similarities with the CityScapes dataset [52], we consider ResNet-38 [16] trained on CityScapes as our teacher network to annotate the training images that have depth but not semantic segmentation.”
MethodVision 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×
“In our experiments, we consider two datasets, NYUDv240 [2], [3] and KITTI [47], [48], representing indoor and outdoor settings, respectively, and both being used extensively in the robotics community.”
BackgroundMethodInfluentialSqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201
Indoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760
Parallel Tracking and Mapping for Small AR Workspaces
Klein, G., & Murray, D. (2007) · 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2007.4538852 · Cited by 4,346
LSD-SLAM: Large-scale direct monocular SLAM
Engel, J., Schöps, T., & Cremers, D. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10605-2_54 · Cited by 3,851
Research works printed but not linked: 28
- qi, 2018, Geonet: Geometric neural network for joint depth and surface normal estimation, CVPR
- 10.1109/IROS.2017.8205954 · DOI
- ba, 2014, Do deep nets really need to be deep?, NIPS
- hinton, 2015, Distilling the knowledge in a neural network, CoRR, abs 1503 2531
- 10.1109/3DV.2016.32 · DOI · Paper page
- 10.1109/ICRA.2017.7989538 · DOI · Paper page
- nekrasov, 2018, Light-weight refinenet for real-time semantic segmentation, BMVC
- 10.1007/s11263-009-0275-4 · DOI · Paper page
- eigen, 2014, Depth map prediction from a single image using a multi-scale deep network, NIPS
- 10.1109/CVPR.2015.7299022 · DOI · Paper page
- couprie, 2013, Indoor semantic segmentation using depth information, arXiv preprint arXiv 1301 3572
- 10.1177/0278364916669237 · DOI · Paper page
- 10.1109/CVPR.2017.579 · DOI · Paper page
- 10.1109/ICCV.2017.447 · DOI · Paper page
- li, 2017, Learning without forgetting, TPAMI
- kendall, 2017, Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, CoRR, abs 1705 7115
- 10.1109/WACV.2018.00145 · DOI
- 10.1109/CVPR.2015.7298965 · DOI · Paper page
- wu, 2016, Wider or deeper: Revisiting the resnet model for visual recognition, CoRR, abs 1611 10080
- chen, 2017, Rethinking atrous convolution for semantic image segmentation, CoRR, abs 1706 5587
- 10.1109/CVPR.2017.684 · DOI · Paper page
- ren, 2015, Faster R-CNN: towards real-time object detection with region proposal networks, CoRR, abs 1506 1497
- 10.1109/CVPR.2013.79 · DOI · Paper page
- iandola, 2016, Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <1mb model size, CoRR, abs 1602 7360
- 10.1016/B978-1-55860-307-3.50012-5 · DOI · Paper page
- zuo, 2017, Fast residual forests: Rapid ensemble learning for semantic segmentation, CoRL
- 10.1109/WACV.2015.38 · DOI
- 10.1109/3DV.2016.69 · DOI · Paper page
Cited by
Multi-Task Learning for Dense Prediction Tasks: A Survey
Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D., & Van Gool, L. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3054719 · Cited by 840
Enforcing Geometric Constraints of Virtual Normal for Depth Prediction
Yin, W., Liu, Y., Shen, C., & Yan, Y. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00578 · Cited by 488
Self-citationXia, W., Zhang, Y., Yang, Y., Xue, J.-H., Zhou, B., & Yang, M.-H. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3181070 · Cited by 366
Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
Luo, G., Zhou, Y., Sun, X., Cao, L., Wu, C., Deng, C., & Ji, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01005 · Cited by 308
Visual Odometry Revisited: What Should Be Learnt?
Zhan, H., Weerasekera, C. S., Bian, J.-W., & Reid, I. (2020) · 2020 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra40945.2020.9197374 · Cited by 201
Self-citation
Metadata
- Authors
- Nekrasov, V., Dharmasiri, T., Spek, A., Drummond, T., Shen, C., & Reid, I.
- Venue
- 2019 International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2019-05
- Pages
- 7101-7107
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2890228252
- Cited by
- 138
- References
- 28
- FWCI
- 6.83
- 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: Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations. https://app.cochat.ai/papers/10.1109/icra.2019.8794220
- The paper
- Nekrasov, V., Dharmasiri, T., Spek, A., Drummond, T., Shen, C., & Reid, I. (2019). Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations. 2019 International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra.2019.8794220
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.