Completely Self-Supervised Crowd Counting via Distribution Matching
Dense crowd counting is a challenging task that demands millions of head annotations for training models. Though existing self-supervised approaches could learn good representations, they require some labeled data to map these features to the end task of density estimation. We mitigate this issue with the proposed paradigm of complete self-supervision, which does not need even a single labeled image. The only input required to train, apart from a large set of unlabeled crowd images, is the approximate upper limit of the crowd count for the given dataset. Our method dwells on the idea that natural crowds follow a power law distribution, which could be leveraged to yield error signals for backpropagation. A density regressor is first pretrained with self-supervision and then the distribution of predictions is matched to the prior by optimizing Sinkhorn distance between the two. Experiments show that this results in effective learning of crowd features and delivers significant counting performance. Furthermore, we establish the superiority of our method in less data setting as well. The code and models for our approach is available at https://github.com/val-iisc/css-ccnn.
Code (1)
Tasks
Crowd CountingDensity EstimationSimilar Papers 제목 키워드 기반
A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i.e., objects are labeled with points) to estimate both the cen…
Crowd CountingObjectobject-detectionObject DetectionReinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting
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 CountingSemi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single d…
Crowd CountingDecoderSelf-Supervised LearningSemi-Supervised Crowd Counting via Self-Training on Surrogate Tasks
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 CountingTransCrowd: weakly-supervised crowd counting with transformers
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