Variational Pedestrian Detection
arXiv:2104.12389
Abstract
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.
References in corpus (9)
- Auto-Encoding Variational Bayes
- YOLOv3: An Incremental Improvement
- MMDetection: Open MMLab Detection Toolbox and Benchmark
- CrowdHuman: A Benchmark for Detecting Human in a Crowd
- FreeAnchor: Learning to Match Anchors for Visual Object Detection
- Towards Accurate One-Stage Object Detection with AP-Loss
- HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces
- Double Anchor R-CNN for Human Detection in a Crowd
- LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object Detection