-
Iterative Crowd Counting
In this work, we tackle the problem of crowd counting in images. We pres...
read it
-
Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression
Accurate cell counting in microscopic images is important for medical di...
read it
-
Feature-aware Adaptation and Structured Density Alignment for Crowd Counting in Video Surveillance
With the development of deep neural networks, the performance of crowd c...
read it
-
Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks
Most existing crowd counting systems rely on the availability of the obj...
read it
-
Active Crowd Counting with Limited Supervision
To learn a reliable people counter from crowd images, head center annota...
read it
-
CODA: Counting Objects via Scale-aware Adversarial Density Adaption
Recent advances in crowd counting have achieved promising results with i...
read it
-
Domain-adaptive Crowd Counting via Inter-domain Features Segregation and Gaussian-prior Reconstruction
Recently, crowd counting using supervised learning achieves a remarkable...
read it
Uncertainty Estimation and Sample Selection for Crowd Counting
We present a method for image-based crowd counting, one that can predict a crowd density map together with the uncertainty values pertaining to the predicted density map. To obtain prediction uncertainty, we model the crowd density values using Gaussian distributions and develop a convolutional neural network architecture to predict these distributions. A key advantage of our method over existing crowd counting methods is its ability to quantify the uncertainty of its predictions. We illustrate the benefits of knowing the prediction uncertainty by developing a method to reduce the human annotation effort needed to adapt counting networks to a new domain. We present sample selection strategies which make use of the density and uncertainty of predictions from the networks trained on one domain to select the informative images from a target domain of interest to acquire human annotation. We show that our sample selection strategy drastically reduces the amount of labeled data from the target domain needed to adapt a counting network trained on a source domain to the target domain. Empirically, the networks trained on UCF-QNRF dataset can be adapted to surpass the performance of the previous state-of-the-art results on NWPU dataset and Shanghaitech dataset using only 17% of the labeled training samples from the target domain.
READ FULL TEXT
Comments
There are no comments yet.