Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Mingyue, Chen, Binghui, Yan, Zhaoyi, Wang, Yaowei, Ye, Qixiang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914668893700096
author Guo, Mingyue
Chen, Binghui
Yan, Zhaoyi
Wang, Yaowei
Ye, Qixiang
author_facet Guo, Mingyue
Chen, Binghui
Yan, Zhaoyi
Wang, Yaowei
Ye, Qixiang
contents Multidomain crowd counting aims to learn a general model for multiple diverse datasets. However, deep networks prefer modeling distributions of the dominant domains instead of all domains, which is known as domain bias. In this study, we propose a simple-yet-effective Modulating Domain-specific Knowledge Network (MDKNet) to handle the domain bias issue in multidomain crowd counting. MDKNet is achieved by employing the idea of `modulating', enabling deep network balancing and modeling different distributions of diverse datasets with little bias. Specifically, we propose an Instance-specific Batch Normalization (IsBN) module, which serves as a base modulator to refine the information flow to be adaptive to domain distributions. To precisely modulating the domain-specific information, the Domain-guided Virtual Classifier (DVC) is then introduced to learn a domain-separable latent space. This space is employed as an input guidance for the IsBN modulator, such that the mixture distributions of multiple datasets can be well treated. Extensive experiments performed on popular benchmarks, including Shanghai-tech A/B, QNRF and NWPU, validate the superiority of MDKNet in tackling multidomain crowd counting and the effectiveness for multidomain learning. Code is available at \url{https://github.com/csguomy/MDKNet}.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03758
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting
Guo, Mingyue
Chen, Binghui
Yan, Zhaoyi
Wang, Yaowei
Ye, Qixiang
Computer Vision and Pattern Recognition
Multidomain crowd counting aims to learn a general model for multiple diverse datasets. However, deep networks prefer modeling distributions of the dominant domains instead of all domains, which is known as domain bias. In this study, we propose a simple-yet-effective Modulating Domain-specific Knowledge Network (MDKNet) to handle the domain bias issue in multidomain crowd counting. MDKNet is achieved by employing the idea of `modulating', enabling deep network balancing and modeling different distributions of diverse datasets with little bias. Specifically, we propose an Instance-specific Batch Normalization (IsBN) module, which serves as a base modulator to refine the information flow to be adaptive to domain distributions. To precisely modulating the domain-specific information, the Domain-guided Virtual Classifier (DVC) is then introduced to learn a domain-separable latent space. This space is employed as an input guidance for the IsBN modulator, such that the mixture distributions of multiple datasets can be well treated. Extensive experiments performed on popular benchmarks, including Shanghai-tech A/B, QNRF and NWPU, validate the superiority of MDKNet in tackling multidomain crowd counting and the effectiveness for multidomain learning. Code is available at \url{https://github.com/csguomy/MDKNet}.
title Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.03758