The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
Open accessAbstract
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations. Without learning from much richer context, these models often fail in challenging scenarios, e.g., severe occlusion, ambiguous lanes, and poor lighting conditions. In this paper, we present a novel knowledge distillation approach, i.e., Self Attention Distillation (SAD), which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels. Specifically, we observe that attention maps extracted from a model trained to a reasonable level would encode rich contextual information. The valuable contextual information can be used as a form of `free' supervision for further representation learning through performing top- down and layer-wise attention distillation within the net- work itself. SAD can be easily incorporated in any feed- forward convolutional neural networks (CNN) and does not increase the inference time. We validate SAD on three popular lane detection benchmarks (TuSimple, CULane and BDD100K) using lightweight models such as ENet, ResNet- 18 and ResNet-34. The lightest model, ENet-SAD, performs comparatively or even surpasses existing algorithms. Notably, ENet-SAD has 20 × fewer parameters and runs 10 × faster compared to the state-of-the-art SCNN, while still achieving compelling performance in all benchmarks.
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
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Multi-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738 · cited 1×
“Dilated convolution [22] is added to replace the original convolution layers in the lane existence prediction branch to increase the receptive field of the network without increasing the number of parameters.”
MethodLarge-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795
Residual Attention Network for Image Classification
Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., & Tang, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.683 · Cited by 4,073
Holistically-Nested Edge Detection
Xie, S., & Tu, Z. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.164 · Cited by 3,096
Zagoruyko, S., & Komodakis, N. (2016) · arXiv · doi:10.48550/arxiv.1612.03928 · Cited by 2,027
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
Paszke, A., Chaurasia, A., Kim, S., & Culurciello, E. (2016) · arXiv · doi:10.48550/arxiv.1606.02147 · Cited by 1,826 · cited 5×
“We further present several architectural reformulations to ENet [17] for improved performance.”
BackgroundMethodInfluentialA Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning
Yim, J., Joo, D., Bae, J., & Kim, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.754 · Cited by 1,570
Attention to Scale: Scale-Aware Semantic Image Segmentation
Chen, L.-C., Yang, Y., Wang, J., Xu, W., & Yuille, A. L. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.396 · Cited by 1,377
Cited by
Knowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931
Ultra Fast Structure-Aware Deep Lane Detection
Qin, Z., Wang, H., & Li, X. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58586-0_17 · Cited by 554
Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection
Tabelini, L., Berriel, R., Paixao, T. M., Badue, C., De Souza, A. F., & Oliveira-Santos, T. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00036 · Cited by 478
YOLOP: You Only Look Once for Panoptic Driving Perception
Wu, D., Liao, M.-W., Zhang, W.-T., Wang, X.-G., Bai, X., Cheng, W.-Q., & Liu, W.-Y. (2022) · Machine Intelligence Research · doi:10.1007/s11633-022-1339-y · Cited by 466
Computing Systems for Autonomous Driving: State of the Art and Challenges
Liu, L., Lu, S., Zhong, R., Wu, B., Yao, Y., Zhang, Q., & Shi, W. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3043716 · Cited by 450
PolyLaneNet: Lane Estimation via Deep Polynomial Regression
Tabelini, L., Berriel, R., Paixao, T. M., Badue, C., De Souza, A. F., & Oliveira-Santos, T. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9412265 · Cited by 366
Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
Ko, Y., Lee, Y., Azam, S., Munir, F., Jeon, M., & Pedrycz, W. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3088488 · Cited by 358
CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
Liu, L., Chen, X., Zhu, S., & Tan, P. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00375 · Cited by 346
End-to-end Lane Shape Prediction with Transformers
Liu, R., Yuan, Z., Liu, T., & Xiong, Z. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00374 · Cited by 338
RESA: Recurrent Feature-Shift Aggregator for Lane Detection
Zheng, T., Fang, H., Zhang, Y., Tang, W., Yang, Z., Liu, H., & Cai, D. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i4.16469 · Cited by 310
Lightweight Deep Learning for Resource-Constrained Environments: A Survey
Liu, H.-I., Galindo, M., Xie, H., Wong, L.-K., Shuai, H.-H., Li, Y.-H., & Cheng, W.-H. (2024) · ACM Computing Surveys · doi:10.1145/3657282 · Cited by 259
Visual Perception Enabled Industry Intelligence: State of the Art, Challenges and Prospects
Yang, J., Wang, C., Jiang, B., Song, H., & Meng, Q. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2998818 · Cited by 258
Yang, W., Li, Q., Liu, W., Yu, Y., Ma, Y., He, S., & Pan, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01528 · Cited by 89
Towards Federated Learning against Noisy Labels via Local Self-Regularization
Jiang, X., Sun, S., Wang, Y., & Liu, M. (2022) · Proceedings of the 31st ACM International Conference on Information & Knowledge Management · doi:10.1145/3511808.3557475 · Cited by 65
“Existing methods usually exploit knowledge from model itself [14] or distill knowledge between different network layers [20, 71].”
Method
Metadata
- Authors
- Hou, Y., Ma, Z., Liu, C., & Loy, C. C.
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 1013-1021
- OpenAlex
- W2981441441
- Cited by
- 780
- References
- 23
- FWCI
- 25.55
- 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.