Scalable Receptive Field GAN: An End-to-End Adversarial Learning Framework for Crowd Counting

Gao, Yukang; Yang, Hua

doi:10.1007/978-3-030-31723-2_36

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods [1,2] achieve superior performance based on the multi-column structure with different receptive fields. In the following works, lower errors are realized through adding extra modules and estimating contexts at various levels [3,4] or introducing dilated kernels [5] or adopting the GAN based framework [6,7]. As shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

Crowd Counting Via Multi-Level Regression With Latent Gaussian Maps

Gao

Yang²

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Crowd counting still confronts two primary challenges: limited ability to deal with cross density levels caused by fixed density maps and lack of fine-grained or coarse-grained guidance for density estimation. In this paper, a novel end-to-end crowd counting framework via multi-level regression with latent Gaussian maps is proposed, which is consisted of GaussianNet, EstimateNet and Discriminator. GaussianNet is composed of masked Gaussian convolutional blocks and vanillia convolutional layers, to generate latent Gaussian maps adaptively for various density levels. The latent Gaussian maps are then treated as the ground truth density maps for EstimateNet, which outputs density estimations and follows the principle of adversarial learning with Discriminator. Moreover, multi-level losses are combined for density map regression guidance. Extensive experiments on the major public datasets outperform state-of-the-art ones, illustrating the superior validity of the proposed framework.

show abstract