paper-with-me

Papers

Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification

2021-05-20 · Haoyue Bai, Song Wen, S. -H. Gary Chan

Labeled crowd scene images are expensive and scarce. To significantly reduce the requirement of the labeled images, we propose ColorCount, a novel CNN-based approach by combining self-supervised transfer colorization learning and global prior classification to leverage the abundantly available unlabeled data. The self-supervised colorization branch learns the semantics and surface texture of the image by using its color components as pseudo labels. The classification branch extracts global group priors by learning correlations among image clusters. Their fused resultant discriminative features (global priors, semantics and textures) provide ample priors for counting, hence significantly reducing the requirement of labeled images. We conduct extensive experiments on four challenging benchmarks. ColorCount achieves much better performance as compared with other unsupervised approaches. Its performance is close to the supervised baseline with substantially less labeled data (10\% of the original one).

📄 PDF Abstract BibTeX arXiv:2105.09684

Code (0)

등록된 구현이 없습니다.

Tasks

ColorizationCrowd Counting

Methods 이 논문이 사용한 방법론

Colorization Colorization is a self-supervision approach that relies on colorization as the pretext task in order to learn image representations.

Similar Papers 제목 키워드 기반

Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer

2020-08-12 · Yuting Liu, Zheng Wang, Miaojing Shi, Shin'ichi Satoh 외

Unsupervised crowd counting is a challenging yet not largely explored task. In this paper, we explore it in a transfer learning setting where we learn to detect and count persons in an unlabeled target set by transferrin…

Crowd CountingKnowledge DistillationregressionSelf-Supervised Learning+1

Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting

2022-02-22 · Xiaoshuang Chen, Hongtao Lu

Fully-supervised crowd counting is a laborious task due to the large amounts of annotations. Few works focus on weekly-supervised crowd counting, where only the global crowd numbers are available for training. The main c…

Crowd Counting

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

2020-07-07 · ECCV 2020 8 · Yan Liu, Lingqiao Liu, Peng Wang, Pingping Zhang 외

Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain. To reduce the annotation cost, one attractive solution is to leverage a large number of un…

Crowd Counting

TransCrowd: weakly-supervised crowd counting with transformers

2021-04-19 · Dingkang Liang, Xiwu Chen, Wei Xu, Yu Zhou 외

The mainstream crowd counting methods usually utilize the convolution neural network (CNN) to regress a density map, requiring point-level annotations. However, annotating each person with a point is an expensive and lab…

Crowd Counting

Semi-Supervised Crowd Counting from Unlabeled Data

2021-08-31 · Haoran Duan, Fan Wan, Rui Sun, Zeyu Wang 외

Automatic Crowd behavior analysis can be applied to effectively help the daily transportation statistics and planning, which helps the smart city construction. As one of the most important keys, crowd counting has drawn …

Crowd Counting