mlsanityData to 7 Oct 2026

Variational Pedestrian Detection

arXiv 2104.12389 ↗First posted 26 Apr 2021cs.CV cs.LG eess.IVcited by 10

Not on the map. Why?

Abstract (arXiv)

Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods. In this paper, we develop a unique perspective of pedestrian detection as a variational inference problem. We formulate a novel and efficient algorithm for pedestrian detection by modeling the dense proposals as a latent variable while proposing a customized Auto Encoding Variational Bayes (AEVB) algorithm. Through the optimization of our proposed algorithm, a classical detector can be fashioned into a variational pedestrian detector. Experiments conducted on CrowdHuman and CityPersons datasets show that the proposed algorithm serves as an efficient solution to handle the dense pedestrian detection problem for the case of single-stage detectors. Our method can also be flexibly applied to two-stage detectors, achieving notable performance enhancement.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 26 Apr 2021.

Builds on

36 of 45 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Fast R-CNNcited by 2,930
  9. 2018YOLOv3: An Incremental Improvementcited by 2,652
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
24 more
  1. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  2. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  3. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  4. 2017Relation Networks for Object Detectioncited by 305
  5. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  6. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  7. 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 171
  8. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 140
  9. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  10. 2017Learning non-maximum suppressioncited by 112
  11. 2019Adaptive NMS: Refining Pedestrian Detection in a Crowdcited by 66
  12. 2017Repulsion Loss: Detecting Pedestrians in a Crowdcited by 62
  13. 2020Detection in Crowded Scenes: One Proposal, Multiple Predictionscited by 59
  14. 2018Occlusion-aware R-CNN: Detecting Pedestrians in a Crowdcited by 58
  15. 2016Is Faster R-CNN Doing Well for Pedestrian Detection?cited by 37
  16. 2019Towards Accurate One-Stage Object Detection with AP-Losscited by 36
  17. 2016The Generalized Reparameterization Gradientcited by 30
  18. 2019PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenescited by 30
  19. 2019Relational Learning for Joint Head and Human Detectioncited by 14
  20. 2019Double Anchor R-CNN for Human Detection in a Crowdcited by 10
  21. 2020Generalizable Pedestrian Detection: The Elephant In The Roomcited by 9
  22. 2019Semantic Head Enhanced Pedestrian Detection in a Crowdcited by 8
  23. 2019HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Facescited by 4
  24. 2019LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object Detectioncited by 2

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 4.

10 papers.

  1. 2022Improving Crowded Object Detection via Copy-Pastecited by 6
  2. 2023Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detectioncited by 3
  3. 2024Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bankcited by 3
  4. 2022RefCrowd: Grounding the Target in Crowd with Referring Expressionscited by 2
  5. 2023BPJDet: Extended Object Representation for Generic Body-Part Joint Detectioncited by 2
  6. 2024PBADet: A One-Stage Anchor-Free Approach for Part-Body Associationcited by 1
  7. 2024Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completioncited by 1
  8. 2022TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detectioncited by 0
  9. 2023Ranking-based Adaptive Query Generation for DETRs in Crowded Pedestrian Detectioncited by 0
  10. 2024IVAC-P2L: Leveraging Irregular Repetition Priors for Improving Video Action Countingcited by 0