mlsanityData to 7 Oct 2026

Wide Aspect Ratio Matching for Robust Face Detection

arXiv 2103.05993 ↗First posted 10 Mar 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, anchor-based methods have achieved great progress in face detection. Once anchor design and anchor matching strategy determined, plenty of positive anchors will be sampled. However, faces with extreme aspect ratio always fail to be sampled according to standard anchor matching strategy. In fact, the max IoUs between anchors and extreme aspect ratio faces are still lower than fixed sampling threshold. In this paper, we firstly explore the factors that affect the max IoU of each face in theory. Then, anchor matching simulation is performed to evaluate the sampling range of face aspect ratio. Besides, we propose a Wide Aspect Ratio Matching (WARM) strategy to collect more representative positive anchors from ground-truth faces across a wide range of aspect ratio. Finally, we present a novel feature enhancement module, named Receptive Field Diversity (RFD) module, to provide diverse receptive field corresponding to different aspect ratios. Extensive experiments show that our method can help detectors better capture extreme aspect ratio faces and achieve promising detection performance on challenging face detection benchmarks, including WIDER FACE and FDDB datasets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 57 references that are in the map. First posted on arXiv 10 Mar 2021.

Builds on

37 of 57 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2015Fast R-CNNcited by 2,930
  7. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  8. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  9. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  10. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  11. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  12. 2016UnitBox: An Advanced Object Detection Networkcited by 205
25 more
  1. 2015MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systemscited by 195
  2. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  3. 2017S3FD: Single Shot Scale-invariant Face Detectorcited by 142
  4. 2018Look at Boundary: A Boundary-Aware Face Alignment Algorithmcited by 137
  5. 2018DSFD: Dual Shot Face Detectorcited by 115
  6. 2016A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detectioncited by 83
  7. 2016Finding Tiny Facescited by 72
  8. 2018PyramidBox: A Context-assisted Single Shot Face Detectorcited by 57
  9. 2017FaceBoxes: A CPU Real-time Face Detector with High Accuracycited by 44
  10. 2015From Facial Parts Responses to Face Detection: A Deep Learning Approachcited by 42
  11. 2017SSH: Single Stage Headless Face Detectorcited by 40
  12. 2016Face Detection with the Faster R-CNNcited by 34
  13. 2018Selective Refinement Network for High Performance Face Detectioncited by 21
  14. 2019RefineFace: Refinement Neural Network for High Performance Face Detectioncited by 21
  15. 2017Face Detection using Deep Learning: An Improved Faster RCNN Approachcited by 16
  16. 2016CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detectioncited by 14
  17. 2018FA-RPN: Floating Region Proposals for Face Detectioncited by 12
  18. 2017Pose-Invariant Face Alignment with a Single CNNcited by 11
  19. 2018Seeing Small Faces from Robust Anchor's Perspectivecited by 11
  20. 2014Aggregate channel features for multi-view face detectioncited by 8
  21. 2017Feature Agglomeration Networks for Single Stage Face Detectioncited by 6
  22. 2014A Fast and Accurate Unconstrained Face Detectorcited by 5
  23. 2017Recurrent Scale Approximation for Object Detection in CNNcited by 5
  24. 2016Face Detection with End-to-End Integration of a ConvNet and a 3D Modelcited by 4
  25. 2017To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detectioncited by 4

Built on by

Not cited yet.