DBScholar

Back to papers

Automatic Road Extraction with Multi-Source Data Revisited: Completeness, Smoothness and Discrimination

Summary: End-to-end revisit of multi-source road extraction: dual encoders fused with attention to enhance inter-source complementarity, plus an edge-prediction auxiliary task to yield smoother, continuous road masks. Introduces pixel-aware contrastive learning to suppress road-like false positives and a model-agnostic auxiliary-task pretraining to boost accuracy; validated on real datasets. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13328
Venue
VLDB
Year
2023
Pagerank
5.093636e-05
Overall Rank
11,452 | 21.43%
DOI
10.14778/3611479.3611504

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{yuan_vldb23,
        title = {{Automatic Road Extraction with Multi-Source Data Revisited: Completeness, Smoothness and Discrimination}},
        author = {Yuan, Haitao and Wang, Sai and Bao, Zhifeng and Wang, Shangguang},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {11},
        pages = {3004--3017},
        doi = {10.14778/3611479.3611504},
        url = {https://doi.org/10.14778/3611479.3611504},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 9 of 9 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers