• Home
  • Search
  • Exploiting sample correlation for crowd counting with multi-expert network
  • Open Access IconOpen Access
  • Cite Icon33
  • https://doi.org/10.1109/iccv48922.2021.00320Copy DOI Icon

Exploiting sample correlation for crowd counting with multi-expert network

  • Oct 1, 2021
  • Xinyan Liu +6 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Crowd counting is a difficult task because of the diversity of scenes. Most of the existing crowd counting methods adopt complex structures with massive backbones to enhance the generalization ability. Unfortunately, the performance of existing methods on large-scale data sets is not satisfactory. In order to handle various scenarios with less complex network, we explored how to efficiently use the multi-expert model for crowd counting tasks. We mainly focus on how to train more efficient expert networks and how to choose the most suitable expert. Specifically, we propose a task-driven similarity metric based on sample’s mutual enhancement, referred as co-fine-tune similarity, which can find a more efficient subset of data for training the expert network. Similar samples are considered as a cluster which is used to obtain parameters of an expert. Besides, to make better use of the proposed method, we design a simple network called FPN with Deconvolution Counting Network, which is a more suitable base model for the multi-expert counting network. Experimental results show that multiple experts FDC (MFDC) achieves the best performance on four public data sets, including the large scale NWPU-Crowd data set. Furthermore, the MFDC trained on an extensive dense crowd data set can generalize well on the other data sets without extra training or fine-tuning. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Similar Papers
  • Conference Article
  • Citations39

MM-Cubing: computing Iceberg cubes by factorizing the lattice space

  • Jun 21, 2004
  • Shu Zheng +2
  • Research Article
  • Citations13

Adversarial scale-adaptive neural network for crowd counting

  • Apr 13, 2021
  • Neurocomputing
  • Xinyue Chen +4
  • Book Chapter

8 Face mask detection and crowd size estimation using IoT platform

  • Feb 06, 2023
  • Vaibhav Tasgaonkar +3
  • Research Article
  • Citations13

A hybrid model of convolutional neural networks and deep regression forests for crowd counting

  • Mar 25, 2020
  • Applied Intelligence
  • Qingge Ji +2
  • Research Article
  • Citations5

Sequential Pattern Mining from Multidimensional Sequence Data in Parallel

  • Jan 01, 2010
  • International Journal of Computer Theory and Engineering
  • Mahdi Esmaieli +1
  • Conference Article

Improving Crowd Counting with Multi-Task Multi-Scale Convolutional Neural Network

  • Jul 01, 2018
  • Siqi Tang +3
  • Book Chapter
  • Citations46

Bringing the Algorithms to the Data: Cloud–Based Benchmarking for Medical Image Analysis

  • Jan 01, 2012
  • Allan Hanbury +5
  • Conference Article
  • Citations7

&lt;title&gt;Remote transformation and local 3D reconstruction and visualization of biomedical data sets in Java3D&lt;/title&gt;

  • Mar 11, 2002
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Pujita Pinnamaneni +2
  • Book Chapter
  • Citations1

Accelerating Topic Detection on Web for a Large-Scale Data Set via Stochastic Poisson Deconvolution

  • Dec 08, 2018
  • Jinzhong Lin +4
  • Conference Article

Research on Crowd Counting Network Model based on Fusion of Shuffle-net and Inception Model

  • Oct 14, 2020
  • Junbo Huang +2
  • Peer Review Report

Decision letter: THINGS-data, a multimodal collection of large-scale datasets for investigating object representations in human brain and behavior

  • Oct 26, 2022
  • Talia Konkle +1
  • Research Article

Thoughts on submarine structural acoustics

  • Oct 01, 2011
  • The Journal of the Acoustical Society of America
  • Ira Dyer
  • Conference Article
  • Citations9

Fast Keyword Searching Using 'BoostMap' Based Embedding

  • Sep 01, 2012
  • Raid Saabni +1
  • PDF
  • Research Article

A Deep Learning Approach for Crowd Counting in Highly Congested Scene

  • Jan 01, 2022
  • Computers, Materials &amp; Continua
  • Akbar Khan +7
  • Conference Article
  • Citations2

An incremental algorithm for frequent itemset mining on spark

  • Mar 01, 2017
  • Min Yu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.