Small Object Sensitive Segmentation of Urban Street Scene With Spatial Adjacency Between Object Classes
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Recent advancements in deep learning have shown exciting promise in the urban street scene segmentation. However, many objects, such as poles and sign symbols, are relatively small and they usually cannot be accurately segmented since the larger objects usually contribute more to the segmentation loss. In this paper, we propose a new boundary-based metric that measures the level of spatial adjacency between each pair of object classes and find that this metric is robust against object size induced biases. We develop a new method to enforce this metric into the segmentation loss. We propose a network, which starts with a segmentation network, followed by a new encoder to compute the proposed boundary-based metric, and then trains this network in an end-to-end fashion. In deployment, we only use the trained segmentation network, without the encoder, to segment new unseen images. Experimentally, we evaluate the proposed method using CamVid and CityScapes datasets and achieve a favorable overall performance improvement and a substantial improvement in segmenting small objects.
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 classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
Riedmiller, M., & Braun, H. (2002) · IEEE International Conference on Neural Networks · doi:10.1109/icnn.1993.298623 · Cited by 3,917 · cited 1×
“t the network parameters must exist [38].”
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
Krähenbühl, P., & Koltun, V. (2012) · arXiv · doi:10.48550/arxiv.1210.5644 · Cited by 2,908
Conditional Random Fields as Recurrent Neural Networks
Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., & Torr, P. H. S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.179 · Cited by 2,386 · cited 2×
“the network [17] and the network cannot adapt its weights based on the post-processing outputs [29].”
BackgroundLarge Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network
Peng, C., Zhang, X., Yu, G., Luo, G., & Sun, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.189 · Cited by 1,750 · cited 10×
“, FCN-8s [14], SegNet [15], GCN [16], PSPNet [18], and DeepLabV3 [12]), and the baseline segmentation network with feature pyramid network-based architecture (e.”
BackgroundInfluentialA convolutional neural network cascade for face detection
Li, H., Lin, Z., Shen, X., Brandt, J., & Hua, G. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299170 · Cited by 1,390
Perceptual Generative Adversarial Networks for Small Object Detection
Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., & Yan, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.211 · Cited by 953 · cited 5×
“Based on the object size [22], we denote sign symbol, pedestrian, pole, bicyclist as small-object classes.”
BackgroundMethodInfluentialYang, F., Choi, W., & Lin, Y. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.234 · Cited by 608 · cited 4×
“In [20], network is trained to generate multi-scale representation which enhances high-level small-scale features”
BackgroundInfluentialDetecting unexpected obstacles for self-driving cars: Fusing deep learning and geometric modeling
Ramos, S., Gehrig, S., Pinggera, P., Franke, U., & Rother, C. (2017) · 2017 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2017.7995849 · Cited by 170
Cited by
YOLOv4-5D: An Effective and Efficient Object Detector for Autonomous Driving
Cai, Y., Luan, T., Gao, H., Wang, H., Chen, L., Li, Y., Sotelo, M. A., & Li, Z. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3065438 · Cited by 340
Li, J., Xu, Z., Fu, L., Zhou, X., & Yu, H. (2021) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.102946 · Cited by 80
Self-citationRLDS: An explainable residual learning diagnosis system for fetal congenital heart disease
Qiao, S., Pang, S., Luo, G., Pan, S., Yu, Z., Chen, T., & Lv, Z. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2021.10.001 · Cited by 42
A novel framework for segmentation of small targets in medical images
Zhao, L., Wang, T., Chen, Y., Zhang, X., Tang, H., Lin, F., Li, C., Li, Q., Tan, T., Kang, D., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-94437-9 · Cited by 24
Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM
Zhang, Y., Mao, Y., Wang, H., Yu, Z., Guo, S., Zhang, J., Wang, L., & Guo, B. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3547256 · Cited by 1
“The principle of tile partition is enlightened from the “ detect + track ” framework in [19], [20], which facilitates the detection and tracking of special regions in consecutive frames.”
Metadata
- Authors
- Guo, D., Zhu, L., Lu, Y., Yu, H., & Wang, S.
- Venue
- IEEE Transactions on Image Processing
- Published
- 2019-06
- Volume
- 28
- Issue
- 6
- Pages
- 2643-2653
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2906500221
- Cited by
- 56
- References
- 11
- FWCI
- 2.49
- Type
- journal article
- Language
- en
- Open access
- closed
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.