Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Wenhao, Zhang, Jusheng
Format: Preprint
Publié: 2020
Sujets:
Accès en ligne:https://arxiv.org/abs/2002.09053
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916023398039552
author Wang, Wenhao
Zhang, Jusheng
author_facet Wang, Wenhao
Zhang, Jusheng
contents Pedestrian detection benefits from deep learning technology and gains rapid development in recent years. Most of detectors follow general object detection frame, i.e. default boxes and two-stage process. Recently, anchor-free and one-stage detectors have been introduced into this area. However, their accuracies are unsatisfactory. Therefore, in order to enjoy the simplicity of anchor-free detectors and the accuracy of two-stage ones simultaneously, we propose some adaptations based on a detector, Center and Scale Prediction(CSP). The main contributions of our paper are: (1) We improve the robustness of CSP and make it easier to train. (2) We propose a novel method to predict width, namely compressing width. (3) We achieve the second best performance on CityPersons benchmark, i.e. 9.3% log-average miss rate(MR) on reasonable set, 8.7% MR on partial set and 5.6% MR on bare set, which shows an anchor-free and one-stage detector can still have high accuracy. (4) We explore some capabilities of Switchable Normalization which are not mentioned in its original paper. The code is publicly available at https://github.com/WangWenhao0716/Adapted-Center-and-Scale-Prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2002_09053
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Adapted Center and Scale Prediction: More Stable and More Accurate
Wang, Wenhao
Zhang, Jusheng
Computer Vision and Pattern Recognition
Pedestrian detection benefits from deep learning technology and gains rapid development in recent years. Most of detectors follow general object detection frame, i.e. default boxes and two-stage process. Recently, anchor-free and one-stage detectors have been introduced into this area. However, their accuracies are unsatisfactory. Therefore, in order to enjoy the simplicity of anchor-free detectors and the accuracy of two-stage ones simultaneously, we propose some adaptations based on a detector, Center and Scale Prediction(CSP). The main contributions of our paper are: (1) We improve the robustness of CSP and make it easier to train. (2) We propose a novel method to predict width, namely compressing width. (3) We achieve the second best performance on CityPersons benchmark, i.e. 9.3% log-average miss rate(MR) on reasonable set, 8.7% MR on partial set and 5.6% MR on bare set, which shows an anchor-free and one-stage detector can still have high accuracy. (4) We explore some capabilities of Switchable Normalization which are not mentioned in its original paper. The code is publicly available at https://github.com/WangWenhao0716/Adapted-Center-and-Scale-Prediction.
title Adapted Center and Scale Prediction: More Stable and More Accurate
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2002.09053