mlsanityData to 7 Oct 2026

Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching

arXiv 2203.15285 ↗First posted 29 Mar 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

A novel algorithm to detect semantic lines is proposed in this paper. We develop three networks: detection network with mirror attention (D-Net) and comparative ranking and matching networks (R-Net and M-Net). D-Net extracts semantic lines by exploiting rich contextual information. To this end, we design the mirror attention module. Then, through pairwise comparisons of extracted semantic lines, we iteratively select the most semantic line and remove redundant ones overlapping with the selected one. For the pairwise comparisons, we develop R-Net and M-Net in the Siamese architecture. Experiments demonstrate that the proposed algorithm outperforms the conventional semantic line detector significantly. Moreover, we apply the proposed algorithm to detect two important kinds of semantic lines successfully: dominant parallel lines and reflection symmetry axes. Our codes are available at https://github.com/dongkwonjin/Semantic-Line-DRM.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 28 of its 56 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

28 of 56 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2015Fast R-CNNcited by 2,930
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  9. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  10. 2017Residual Attention Network for Image Classificationcited by 385
  11. 2018BAM: Bottleneck Attention Modulecited by 171
  12. 2018QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehensioncited by 164
16 more
  1. 2017RankIQA: Learning from Rankings for No-reference Image Quality Assessmentcited by 150
  2. 2019Pyramid Feature Attention Network for Saliency detectioncited by 128
  3. 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 122
  4. 2018Learn To Pay Attentioncited by 83
  5. 2019End-to-End Wireframe Parsingcited by 72
  6. 2020Learning to Parse Wireframes in Images of Man-Made Environmentscited by 71
  7. 2018Learning Attraction Field Representation for Robust Line Segment Detectioncited by 52
  8. 2019Vehicle Re-identification with Viewpoint-aware Metric Learningcited by 45
  9. 2016Horizon Lines in the Wildcited by 30
  10. 2016Detecting Vanishing Points using Global Image Context in a Non-Manhattan Worldcited by 27
  11. 2015Deep Feature Learning with Relative Distance Comparison for Person Re-identificationcited by 25
  12. 2019NeurVPS: Neural Vanishing Point Scanning via Conic Convolutioncited by 24
  13. 2016Detecting Dominant Vanishing Points in Natural Scenes with Application to Composition-Sensitive Image Retrievalcited by 11
  14. 2016A convolutional approach to reflection symmetrycited by 10
  15. 2017Wavelet-based Reflection Symmetry Detection via Textural and Color Histogramscited by 7
  16. 2019Sem-LSD: A Learning-based Semantic Line Segment Detectorcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 2.

4 papers.

  1. 2022Visual Attention Methods in Deep Learning: An In-Depth Surveycited by 37
  2. 2023Agronav: Autonomous Navigation Framework for Agricultural Robots and Vehicles using Semantic Segmentation and Semantic Line Detectioncited by 9
  3. 2024Semantic Line Combination Detectorcited by 1
  4. 2024Enhancing Surveillance Camera FOV Quality via Semantic Line Detection and Classification with Deep Hough Transformcited by 0