mlsanityData to 7 Oct 2026

CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement

arXiv 2103.07017 ↗First posted 12 Mar 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Face detection is a fundamental problem for many downstream face applications, and there is a rising demand for faster, more accurate yet support for higher resolution face detectors. Recent smartphones can record a video in 8K resolution, but many of the existing face detectors still fail due to the anchor size and training data. We analyze the failure cases and observe a large number of correct predicted boxes with incorrect confidences. To calibrate these confidences, we propose a confidence ranking network with a pairwise ranking loss to re-rank the predicted confidences locally within the same image. Our confidence ranker is model-agnostic, so we can augment the data by choosing the pairs from multiple face detectors during the training, and generalize to a wide range of face detectors during the testing. On WiderFace, we achieve the highest AP on the single-scale, and our AP is competitive with the previous multi-scale methods while being significantly faster. On 8K resolution, our method solves the GPU memory issue and allows us to indirectly train on 8K. We collect 8K resolution test set to show the improvement, and we will release our test set as a new benchmark for future research.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 48 of its 74 references that are in the map. First posted on arXiv 12 Mar 2021.

Builds on

48 of 74 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2015Fast R-CNNcited by 2,930
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  12. 2019Searching for MobileNetV3cited by 1,984
36 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  6. 2019Objects as Pointscited by 1,172
  7. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  8. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  9. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  10. 2017Focal Loss for Dense Object Detectioncited by 749
  11. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  12. 2015WIDER FACE: A Face Detection Benchmarkcited by 297
  13. 2019Mask Scoring R-CNNcited by 265
  14. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  15. 2018Acquisition of Localization Confidence for Accurate Object Detectioncited by 174
  16. 2019Bottom-up Object Detection by Grouping Extreme and Center Pointscited by 156
  17. 2017S3FD: Single Shot Scale-invariant Face Detectorcited by 142
  18. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  19. 2018DSFD: Dual Shot Face Detectorcited by 115
  20. 2016Finding Tiny Facescited by 72
  21. 2018PyramidBox: A Context-assisted Single Shot Face Detectorcited by 57
  22. 2015Object detection via a multi-region & semantic segmentation-aware CNN modelcited by 47
  23. 2017SSH: Single Stage Headless Face Detectorcited by 40
  24. 2019FoveaBox: Beyond Anchor-based Object Detectorcited by 37
  25. 2018Selective Refinement Network for High Performance Face Detectioncited by 21
  26. 2019RefineFace: Refinement Neural Network for High Performance Face Detectioncited by 21
  27. 2019Joint Face Detection and Facial Motion Retargeting for Multiple Facescited by 18
  28. 2015G-CNN: an Iterative Grid Based Object Detectorcited by 13
  29. 2019PyramidBox++: High Performance Detector for Finding Tiny Facecited by 13
  30. 2018FA-RPN: Floating Region Proposals for Face Detectioncited by 12
  31. 2020IterDet: Iterative Scheme for Object Detection in Crowded Environmentscited by 12
  32. 2018Seeing Small Faces from Robust Anchor's Perspectivecited by 11
  33. 2019Accurate Face Detection for High Performancecited by 8
  34. 2017Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wildcited by 7
  35. 2019Robust and High Performance Face Detectorcited by 6
  36. 2020MaskFace: multi-task face and landmark detectorcited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 2.

6 papers.

  1. 2022EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detectioncited by 5
  2. 2022Privacy-preserving Online AutoML for Domain-Specific Face Detectioncited by 4
  3. 2023EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detectioncited by 3
  4. 2022A Survey of Face Recognitioncited by 1
  5. 2021Bounding-box deep calibration for high performance face detectioncited by 0
  6. 2023EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detectioncited by 0