Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network

  title={Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network},
  author={Zhikang Zou and Xiaoye Qu and Pan Zhou and Shuangjie Xu and Xiaoqing Ye and Wenhao Wu and Jin Ye},
  journal={Proceedings of the 29th ACM International Conference on Multimedia},
  • Zhikang Zou, Xiaoye Qu, +4 authors Jin Ye
  • Published 2021
  • Computer Science
  • Proceedings of the 29th ACM International Conference on Multimedia
Recent deep networks have convincingly demonstrated high capability in crowd counting, which is a critical task attracting widespread attention due to its various industrial applications. Despite such progress, trained data-dependent models usually can not generalize well to unseen scenarios because of the inherent domain shift. To facilitate this issue, this paper proposes a novel adversarial scoring network (ASNet) to gradually bridge the gap across domains from coarse to fine granularity. In… Expand


CODA: Counting Objects via Scale-Aware Adversarial Density Adaption
  • L. Wang, Yongbo Li, X. Xue
  • Computer Science
  • 2019 IEEE International Conference on Multimedia and Expo (ICME)
  • 2019
A novel adversarial learning approach to crowd counting, i.e., CODA (Counting Objects via scale-aware adversarial Density Adaption), which is comparable with the state-of-the-art fully-supervised models that are trained on the target dataset. Expand
Leveraging Self-Supervision for Cross-Domain Crowd Counting
This work forces a network to learn perspective-aware features by training it to recognize upside-down real images from regular ones and incorporate into it the ability to predict its own uncertainty so that it can generate useful pseudo labels for fine-tuning purposes. Expand
Discriminative Partial Domain Adversarial Network
In this paper, a novel Discriminative Partial Domain Adversarial Network (DPDAN) is developed and empirically verify DPDAN can effectively reduce the negative transfer caused by source-negative classes, and theoretically show it decreases negativeTransfer caused by domain shift. Expand
Crowd Counting with Deep Negative Correlation Learning
This work proposes a new learning strategy to produce generalizable features by way of deep negative correlation learning (NCL), which deeply learn a pool of decorrelated regressors with sound generalization capabilities through managing their intrinsic diversities. Expand
Crowd Counting With Deep Structured Scale Integration Network
A novel Deep Structured Scale Integration Network (DSSINet) for crowd counting is proposed, which addresses the scale variation of people by using structured feature representation learning and hierarchically structured loss function optimization. Expand
Domain-adaptive Crowd Counting via Inter-domain Features Segregation and Gaussian-prior Reconstruction
A Domain-Adaptive Crowd Counting (DACC) framework, which consists of Inter-domain Features Segregation (IFS) and Gaussian-prior Reconstruction (GPR) and demonstrates that the proposed method outperforms the state-of-the-art methods. Expand
Focus on Semantic Consistency for Cross-Domain Crowd Understanding
  • Tao Han, Junyu Gao, Yuan Yuan, Qi Wang
  • Computer Science
  • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2020
A domain adaptation method to eliminate a mass of estimation errors in the background areas of the synthetic and real-world crowd area and achieves the state-of-the-art for cross-domain counting problems. Expand
DA-Net: Learning the Fine-Grained Density Distribution With Deformation Aggregation Network
The deformation aggregation network (DA-Net) is proposed that can incrementally incorporate adaptive receptive fields to capture the fine-grained density distribution and delivers the state-of-the-art performance on four benchmarks. Expand
Feature-aware Adaptation and Structured Density Alignment for Crowd Counting in Video Surveillance
  • Junyu Gao, Qi Wang, Yuan Yuan
  • Computer Science
  • ArXiv
  • 2019
This paper proposes a domain-adaptation-style crowd counting method, which can effectively adapt the model from synthetic data to the specific real-world scenes, and outperforms the state-of-the-art methods for the same cross-domain counting problem. Expand
Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training
This paper proposes a novel UDA framework based on an iterative self-training (ST) procedure, where the problem is formulated as latent variable loss minimization, and can be solved by alternatively generating pseudo labels on target data and re-training the model with these labels. Expand