Focus on Semantic Consistency for Cross-domain Crowd Understanding

02/20/2020
by   Tao Han, et al.
0

For pixel-level crowd understanding, it is time-consuming and laborious in data collection and annotation. Some domain adaptation algorithms try to liberate it by training models with synthetic data, and the results in some recent works have proved the feasibility. However, we found that a mass of estimation errors in the background areas impede the performance of the existing methods. In this paper, we propose a domain adaptation method to eliminate it. According to the semantic consistency, a similar distribution in deep layer's features of the synthetic and real-world crowd area, we first introduce a semantic extractor to effectively distinguish crowd and background in high-level semantic information. Besides, to further enhance the adapted model, we adopt adversarial learning to align features in the semantic space. Experiments on three representative real datasets show that the proposed domain adaptation scheme achieves the state-of-the-art for cross-domain counting problems.

READ FULL TEXT

page 2

page 4

research
12/08/2019

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...
research
01/09/2020

CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency

Unsupervised domain adaptation algorithms aim to transfer the knowledge ...
research
07/30/2020

Pixel-wise Crowd Understanding via Synthetic Data

Crowd analysis via computer vision techniques is an important topic in t...
research
06/21/2022

Multi-level Domain Adaptation for Lane Detection

We focus on bridging domain discrepancy in lane detection among differen...
research
06/07/2022

Self-supervised Domain Adaptation in Crowd Counting

Self-training crowd counting has not been attentively explored though it...
research
05/12/2022

Bi-level Alignment for Cross-Domain Crowd Counting

Recently, crowd density estimation has received increasing attention. Th...
research
03/30/2021

Leveraging Self-Supervision for Cross-Domain Crowd Counting

State-of-the-art methods for counting people in crowded scenes rely on d...

Please sign up or login with your details

Forgot password? Click here to reset