-
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
-
Learning from Synthetic Data for Crowd Counting in the Wild
Recently, counting the number of people for crowd scenes is a hot topic ...
read it
-
Leveraging Self-Supervision for Cross-Domain Crowd Counting
State-of-the-art methods for counting people in crowded scenes rely on d...
read it
-
Pixel-wise Crowd Understanding via Synthetic Data
Crowd analysis via computer vision techniques is an important topic in t...
read it
-
Learning to Count in the Crowd from Limited Labeled Data
Recent crowd counting approaches have achieved excellent performance. ho...
read it
-
Uncertainty Estimation and Sample Selection for Crowd Counting
We present a method for image-based crowd counting, one that can predict...
read it
-
Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting
Cross-domain crowd counting (CDCC) is a hot topic due to its importance ...
read it
Domain-adaptive Crowd Counting via Inter-domain Features Segregation and Gaussian-prior Reconstruction
Recently, crowd counting using supervised learning achieves a remarkable improvement. Nevertheless, most counters rely on a large amount of manually labeled data. With the release of synthetic crowd data, a potential alternative is transferring knowledge from them to real data without any manual label. However, there is no method to effectively suppress domain gaps and output elaborate density maps during the transferring. To remedy the above problems, this paper proposed a Domain-Adaptive Crowd Counting (DACC) framework, which consists of Inter-domain Features Segregation (IFS) and Gaussian-prior Reconstruction (GPR). To be specific, IFS translates synthetic data to realistic images, which contains domain-shared features extraction and domain-independent features decoration. Then a coarse counter is trained on translated data and applied to the real world. Moreover, according to the coarse predictions, GPR generates pseudo labels to improve the prediction quality of the real data. Next, we retrain a final counter using these pseudo labels. Adaptation experiments on six real-world datasets demonstrate that the proposed method outperforms the state-of-the-art methods. Furthermore, the code and pre-trained models will be released as soon as possible.
READ FULL TEXT
Comments
There are no comments yet.