paper-with-me

홈 › Papers

Progressive Multi-resolution Loss for Crowd Counting

2022-12-08 · Ziheng Yan, Yuankai Qi, Guorong Li, Xinyan Liu, Weigang Zhang, Qingming Huang, Ming-Hsuan Yang

Crowd counting is usually handled in a density map regression fashion, which is supervised via a L2 loss between the predicted density map and ground truth. To effectively regulate models, various improved L2 loss functions have been proposed to find a better correspondence between predicted density and annotation positions. In this paper, we propose to predict the density map at one resolution but measure the density map at multiple resolutions. By maximizing the posterior probability in such a setting, we obtain a log-formed multi-resolution L2-difference loss, where the traditional single-resolution L2 loss is its particular case. We mathematically prove it is superior to a single-resolution L2 loss. Without bells and whistles, the proposed loss substantially improves several baselines and performs favorably compared to state-of-the-art methods on four crowd counting datasets, ShanghaiTech A & B, UCF-QNRF, and JHU-Crowd++.

📄 PDF Abstract BibTeX arXiv:2212.04127

Code (1)

streamer-AP/PML_Loss 공식 구현 pytorch

Tasks

Crowd Counting

Similar Papers 제목 키워드 기반

CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model

2023-04-09 · CVPR 2023 1 · Dingkang Liang, Jiahao Xie, Zhikang Zou, Xiaoqing Ye 외

Supervised crowd counting relies heavily on costly manual labeling, which is difficult and expensive, especially in dense scenes. To alleviate the problem, we propose a novel unsupervised framework for crowd counting, na…

Cross-Part Crowd CountingCrowd CountingLanguage ModelingLanguage Modelling+1

MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery

2019-09-27 · Reza Bahmanyar, Elenora Vig, Peter Reinartz

In spite of the many advantages of aerial imagery for crowd monitoring and management at mass events, datasets of aerial images of crowds are still lacking in the field. As a remedy, in this work we introduce a novel cro…

Crowd CountingDecoderManagement

Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting

2021-04-28 · Haoyue Bai, S. -H. Gary Chan

We study video crowd counting, which is to estimate the number of objects (people in this paper) in all the frames of a video sequence. Previous work on crowd counting is mostly on still images. There has been little wor…

Crowd Counting

Scale Aggregation Network for Accurate and Efficient Crowd Counting

2018-09-01 · ECCV 2018 9 · Xinkun Cao, Zhipeng Wang, Yanyun Zhao, Fei Su

In this paper, we propose a novel encoder-decoder network, called extit{Scale Aggregation Network (SANet)}, for accurate and efficient crowd counting. The encoder extracts multi-scale features with scale aggregation mod…

Crowd CountingDecoder

ProgRoCC: A Progressive Approach to Rough Crowd Counting

2025-04-18 · Shengqin Jiang, Linfei Li, Haokui Zhang, Qingshan Liu 외

As the number of individuals in a crowd grows, enumeration-based techniques become increasingly infeasible and their estimates increasingly unreliable. We propose instead an estimation-based version of the problem: we la…

Crowd Counting