SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Earlier work demonstrates the promise of deep-learning-based approaches for point cloud segmentation; however, these approaches need to be improved to be practically useful. To this end, we introduce a new model SqueezeSegV2. With an improved model structure, SqueezeSetV2 is more robust against dropout noises in LiDAR point cloud and therefore achieves significant accuracy improvement. Training models for point cloud segmentation requires large amounts of labeled data, which is expensive to obtain. To sidestep the cost of data collection and annotation, simulators such as GTA-V can be used to create unlimited amounts of labeled, synthetic data. However, due to domain shift, models trained on synthetic data often do not generalize well to the real world. Existing domain-adaptation methods mainly focus on images and most of them cannot be directly applied to point clouds. We address this problem with a domain-adaptation training pipeline consisting of three major components: 1) learned intensity rendering, 2) geodesic correlation alignment, and 3) progressive domain calibration. When trained on real data, our new model exhibits segmentation accuracy improvements of 6.0-8.6% over the original SqueezeSeg. When training our new model on synthetic data using the proposed domain adaptation pipeline, we nearly double test accuracy on real-world data, from 29.0% to 57.4%. Our source code and synthetic dataset are open sourced. https://github.com/xuanyuzhou98/SqueezeSegV2.
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
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 3×
“In addition to CAM, we adopt several improvements to SqueezeSeg, including using focal loss [4], batch normalization [5], and LiDAR mask as an input channel.”
MethodAre we ready for autonomous driving? The KITTI vision benchmark suite
Geiger, A., Lenz, P., & Urtasun, R. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248074 · Cited by 14,897
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858826 · Cited by 9,556
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Charles, R. Q., Su, H., Kaichun, M., & Guibas, L. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.16 · Cited by 9,237
Domain-Adversarial Training of Neural Networks
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-58347-1_10 · Cited by 8,318
Adversarial Discriminative Domain Adaptation
Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.316 · Cited by 5,154 · cited 1×
“In addition to the task related loss computed from the labeled source data, deep UDA models are usually trained jointly with another loss, such as a discrepancy loss [15], [16], [17], [18], [6], adversarial loss [19], [20], [21], [22], [23], [24], label distribution loss [18] or reconstruction loss [25], [26].”
MethodLearning Transferable Features with Deep Adaptation Networks
Long, M., Cao, Y., Wang, J., & Jordan, M. I. (2015) · arXiv · doi:10.48550/arxiv.1502.02791 · Cited by 4,505
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
Hoffman, J., Tzeng, E., Park, T., Zhu, J.-Y., Isola, P., Saenko, K., Efros, A. A., & Darrell, T. (2017) · arXiv · doi:10.48550/arxiv.1711.03213 · Cited by 2,656 · cited 2×
“The most relevant work is the exploration of synthetic data [22], [18], [24].”
BackgroundMethod
Cited by
Deep Learning for 3D Point Clouds: A Survey
Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., & Bennamoun, M. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3005434 · Cited by 2,398
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
Behley, J., Garbade, M., Milioto, A., Quenzel, J., Behnke, S., Stachniss, C., & Gall, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00939 · Cited by 2,294
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., & Markham, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01112 · Cited by 2,275
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Wu, B., Keutzer, K., Dai, X., Zhang, P., Wang, Y., Sun, F., Wu, Y., Tian, Y., Vajda, P., & Jia, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01099 · Cited by 1,261
Self-citationRangeNet ++: Fast and Accurate LiDAR Semantic Segmentation
Milioto, A., Vizzo, I., Behley, J., & Stachniss, C. (2019) · 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967762 · Cited by 1,240
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
Zhu, X., Zhou, H., Wang, T., Hong, F., Ma, Y., Li, W., Li, H., & Lin, D. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00981 · Cited by 623
PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
Zhang, Y., Zhou, Z., David, P., Yue, X., Xi, Z., Gong, B., & Foroosh, H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00962 · Cited by 590
Self-citationAutomotive LiDAR Technology: A Survey
Roriz, R., Cabral, J., & Gomes, T. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3086804 · Cited by 442
SalsaNext: Fast, Uncertainty-Aware Semantic Segmentation of LiDAR Point Clouds
Cortinhal, T., Tzelepis, G., & Erdal Aksoy, E. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-64559-5_16 · Cited by 430
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
Xu, C., Wu, B., Wang, Z., Zhan, W., Vajda, P., Keutzer, K., & Tomizuka, M. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58604-1_1 · Cited by 430
Self-citationSynthetic Data for Deep Learning
Nikolenko, S. I. (2021) · Springer Optimization and Its Applications · doi:10.1007/978-3-030-75178-4 · Cited by 423
Visual Transformers: Token-based Image Representation and Processing for Computer Vision
Wu, B., Xu, C., Dai, X., Wan, A., Zhang, P., Yan, Z., Tomizuka, M., Gonzalez, J., Keutzer, K., & Vajda, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.03677 · Cited by 357
Self-citationA Review of Single-Source Deep Unsupervised Visual Domain Adaptation
Zhao, S., Yue, X., Zhang, S., Li, B., Zhao, H., Wu, B., Krishna, R., Gonzalez, J. E., Sangiovanni-Vincentelli, A. L., Seshia, S. A., et al. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3028503 · Cited by 352
Self-citationYan, X., Gao, J., Li, J., Zhang, R., Li, Z., Huang, R., & Cui, S. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i4.16419 · Cited by 282
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
Yan, X., Gao, J., Zheng, C., Zheng, C., Zhang, R., Cui, S., & Li, Z. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19815-1_39 · Cited by 280
Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion
Qiu, S., Anwar, S., & Barnes, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00180 · Cited by 275
Cheng, R., Razani, R., Taghavi, E., Li, E., & Liu, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01236 · Cited by 264
Robust Multi-Modality Multi-Object Tracking
Zhang, W., Zhou, H., Sun, S., Wang, Z., Shi, J., & Loy, C. C. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00245 · Cited by 250
xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Jaritz, M., Vu, T.-H., de Charette, R., Wirbel, E., & Perez, P. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01262 · Cited by 224
Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation
Zhuang, Z., Li, R., Jia, K., Wang, Q., Li, Y., & Tan, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01597 · Cited by 216
UniSim: A Neural Closed-Loop Sensor Simulator
Yang, Z., Chen, Y., Wang, J., Manivasagam, S., Ma, W.-C., Yang, A. J., & Urtasun, R. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00140 · Cited by 170
Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey of Datasets and Methods
Gao, B., Pan, Y., Li, C., Geng, S., & Zhao, H. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3076844 · Cited by 105
FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data
Krispel, G., Opitz, M., Waltner, G., Possegger, H., & Bischof, H. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093584 · Cited by 99
“r classes pedestrian and cyclist, by a large margin. We increase the mean intersection-over-union (IoU) by 18% respectively 13.2% compared to SqueezeSeg. We even outperform its successor SqueezeSegV2 [38] on average by 3.1%, which could be improved by our approach as well. 4.2. FuseSeg vs RGB Semantic Segmentation App…”
BackgroundInfluentialLiDAR Panoptic Segmentation for Autonomous Driving
Milioto, A., Behley, J., McCool, C., & Stachniss, C. (2020) · 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340837 · Cited by 98
“In contrast to prior works [27], [45], [46], which upsam-ple the backbone features using transposed convolutions or bilinear upsampling, exploiting closeness in the image, we implement a differentiable trilinear upsampling layer, which exploits the fact that our inputs are 3D point clouds and not…”
MethodResultRecent Advancements in Learning Algorithms for Point Clouds: An Updated Overview
Camuffo, E., Mari, D., & Milani, S. (2022) · Sensors · doi:10.3390/s22041357 · Cited by 73
“SqueezeSegV2 [70] was then introduced to address domain shift, i.”
BackgroundSELMA: SEmantic Large-Scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints
Testolina, P., Barbato, F., Michieli, U., Giordani, M., Zanuttigh, P., & Zorzi, M. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3257086 · Cited by 41
“V2 [77] and DarkNet-21 [78]) and with Cylinder3D [71].”
Metadata
- Authors
- Wu, B., Zhou, X., Zhao, S., Yue, X., & Keutzer, K.
- Venue
- 2019 International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2019-05
- Pages
- 4376-4382
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2968557240
- Cited by
- 726
- References
- 34
- FWCI
- 33.86
- 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.