paper-with-me

Papers

AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting

2020-10-23 · Mahesh Kumar Krishna Reddy, Mrigank Rochan, Yiwei Lu, Yang Wang

We address the problem of image-based crowd counting. In particular, we propose a new problem called unlabeled scene-adaptive crowd counting. Given a new target scene, we would like to have a crowd counting model specifically adapted to this particular scene based on the target data that capture some information about the new scene. In this paper, we propose to use one or more unlabeled images from the target scene to perform the adaptation. In comparison with the existing problem setups (e.g. fully supervised), our proposed problem setup is closer to the real-world applications of crowd counting systems. We introduce a novel AdaCrowd framework to solve this problem. Our framework consists of a crowd counting network and a guiding network. The guiding network predicts some parameters in the crowd counting network based on the unlabeled images from a particular scene. This allows our model to adapt to different target scenes. The experimental results on several challenging benchmark datasets demonstrate the effectiveness of our proposed approach compared with other alternative methods. Code is available at https://github.com/maheshkkumar/adacrowd.

📄 PDF Abstract BibTeX arXiv:2010.12141

Code (1)

maheshkkumar/adacrowd 공식 구현 pytorch

Tasks

Crowd Counting

Similar Papers 제목 키워드 기반

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

2018-03-08 · CVPR 2018 6 · Xialei Liu, Joost Van de Weijer, Andrew D. Bagdanov

We propose a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework. To induce a ranking of cropped images , we use the observation that any sub-image of…

Crowd CountingImage RetrievalLearning-To-RankRetrieval

Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning

2020-02-01 · Mahesh Kumar Krishna Reddy, Mohammad Hossain, Mrigank Rochan, Yang Wang

We consider the problem of few-shot scene adaptive crowd counting. Given a target camera scene, our goal is to adapt a model to this specific scene with only a few labeled images of that scene. The solution to this probl…

Crowd CountingMeta-Learning

Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

2022-01-13 · Jiaqi Gao, Zhizhong Huang, Yiming Lei, Hongming Shan 외

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensiv…

Crowd Counting

Self-supervised Domain Adaptation in Crowd Counting

2022-06-07 · Pha Nguyen, Thanh-Dat Truong, Miaoqing Huang, Yi Liang 외

Self-training crowd counting has not been attentively explored though it is one of the important challenges in computer vision. In practice, the fully supervised methods usually require an intensive resource of manual an…

Crowd CountingDomain Adaptation

Bayesian Model Adaptation for Crowd Counts

2015-12-01 · ICCV 2015 12 · Bo Liu, Nuno Vasconcelos

The problem of transfer learning is considered in the domain of crowd counting. A solution based on Bayesian model adaptation of Gaussian processes is proposed. This is shown to produce intuitive model updates, which are…

Crowd CountingGaussian ProcessesmodelMulti-Task Learning+1