• Home
  • Search
  • Dynamic Momentum Adaptation for Zero-Shot Cross-Domain Crowd Counting
  • Open Access IconOpen Access
  • Cite Icon30
  • https://doi.org/10.1145/3474085.3475230Copy DOI Icon

Dynamic Momentum Adaptation for Zero-Shot Cross-Domain Crowd Counting

  • Oct 17, 2021
  • Qiangqiang Wu +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Zero-shot cross-domain crowd counting is a challenging task where a crowd counting model is trained on a source domain (i.e., training dataset) and no additional labeled or unlabeled data is available for fine-tuning the model when testing on an unseen target domain (i.e., a different testing dataset). The generalisation performance of existing crowd counting methods is typically limited due to the large gap between source and target domains. Here, we propose a novel Crowd Counting framework built upon an external Momentum Template, termed C2MoT, which enables the encoding of domain specific information via an external template representation. Specifically, the Momentum Template (MoT) is learned in a momentum updating way during offline training, and then is dynamically updated for each test image in online cross-dataset evaluation. Thanks to the dynamically updated MoT, our C2MoT effectively generates dense target correspondences that explicitly accounts for head regions, and then effectively predicts the density map based on the normalized correspondence map. Experiments on large scale datasets show that our proposed C2MoT achieves leading zero-shot cross-domain crowd counting performance without model fine-tuning, while also outperforming domain adaptation methods that use fine-tuning on target domain data. Moreover, C2MoT also obtains state-of-the-art counting performance on the source domain.

Similar Papers
  • Conference Article
  • Citations8

Domain Adaptation in Crowd Counting

  • May 01, 2020
  • Mohammad Asiful Hossain +4
  • Conference Article
  • Citations2

Indoor WLAN Intrusion Detection Using Intra-class Transfer Learning with Low Effort

  • Sep 01, 2019
  • Mu Zhou +4
  • Research Article
  • Citations224

Online Transfer Learning

  • Jul 17, 2014
  • Artificial Intelligence
  • Peilin Zhao +3
  • Conference Article
  • Citations22

Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer

  • Sep 19, 2021
  • Jan-Aike Termohlen +4
  • Research Article
  • Citations4

Phrase Grounding-Based Style Transfer for Single-Domain Generalized Object Detection

  • Jan 01, 2026
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Hao Li +8
  • PDF
  • Research Article
  • Citations9

Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning

  • Oct 13, 2021
  • International Journal of Aerospace Engineering
  • Gang Xiang +1
  • Research Article
  • Citations16

Overcoming learning bias via Prototypical Feature Compensation for source-free domain adaptation

  • Sep 17, 2024
  • Pattern Recognition
  • Zicheng Pan +3
  • Research Article
  • Citations1

A novel Pseudo-label based domain adaptation method on tabular data

  • May 04, 2023
  • Journal of Intelligent & Fuzzy Systems
  • Chu Wang +4
  • Research Article
  • Citations53

Online transfer learning by leveraging multiple source domains

  • Jan 11, 2017
  • Knowledge and Information Systems
  • Qingyao Wu +4
  • Research Article
  • Citations4

Bi-adapting kernel learning for unsupervised domain adaptation

  • Jul 27, 2019
  • Neurocomputing
  • Zengmao Wang +4
  • Conference Article
  • Citations140

Generalizable Person Re-identification with Relevance-aware Mixture of Experts

  • Jun 01, 2021
  • Yongxing Dai +4
  • Research Article
  • Citations16

Latent Domain Generation for Unsupervised Domain Adaptation Object Counting

  • Jan 01, 2023
  • IEEE Transactions on Multimedia
  • Anran Zhang +5
  • PDF
  • Research Article

Learning Transferable Convolutional Proxy by SMI-Based Matching Technique

  • Oct 14, 2020
  • Shock and Vibration
  • Wei Jin +1
  • Conference Article
  • Citations3

Modeling Sequential Domain Shift through Estimation of Optimal Sub-spaces for Categorization

  • Jan 01, 2014
  • Suranjana Samanta +2
  • Research Article
  • Citations7

Unsupervised Domain Expansion for Visual Categorization

  • Nov 12, 2021
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jie Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.