Learning From Synthetic Data for Crowd Counting in the Wild

Abstract

Recently, counting the number of people for crowd scenes is a hot topic because of its widespread applications (e.g. video surveillance, public security). It is a difficult task in the wild: changeable environment, large-range number of people cause the current methods can not work well. In addition, due to the scarce data, many methods suffer from over-fitting to a different extent. To remedy the above two problems, firstly, we develop a data collector and labeler, which can generate the synthetic crowd scenes and simultaneously annotate them without any manpower. Based on it, we build a large-scale, diverse synthetic dataset. Secondly, we propose two schemes that exploit the synthetic data to boost the performance of crowd counting in the wild: 1) pretrain a crowd counter on the synthetic data, then finetune it using the real data, which significantly prompts the model's performance on real data; 2) propose a crowd counting method via domain adaptation, which can free humans from heavy data annotations. Extensive experiments show that the first method achieves the state-of-the-art performance on four real datasets, and the second outperforms our baselines. The dataset and source code are available at

Focus on Semantic Consistency for Cross-Domain Crowd Understanding

“…In this section, we perform experiments on three typical datasets for across domain crowd counting and then compare the performance of our proposed method with the state-ofthe-art SE Cycle GAN [16]. The test results are shown in Table 1.…”

“…In this paper, the central issue is how to design a better domain adaptation scheme for reducing the counting noise in the background area. After observing a large number of images in the GCC [16] dataset, we find that the characters in the synthetic scene and the real scene have a high degree of visual similarity, while the background has a large gap. This similarity is more obvious in the high-level semantic representation.…”

“…To address the problem of data scarcity in crowd counting, some works [11][12][13] explore unsupervised or weakly supervised crowd counting, but these methods did not completely get rid of the dependence on manually annotated data. Inspired by the application of synthetic data [14,15] in other visual fields, a large-scale crowd counting dataset named GCC was established by Wang et al [16], where the data is generated and annotated automatically by a computer game mod. Although this novel data generation method solves the challenge of manually labeling data, one problem that comes with it is that the gap between the synthetic scenes and the realworld scenes is too large.…”

“…Some of the recent work [17][18][19][20][21] provided us with a domain adaptation strategy, using image style transfer networks to narrow the domain gap. For the cross-domain crowd counting problem, [16] also proposed a domain adaptation method to make synthetic data closer to real data in visual perception via the SE Cycle GAN [16] network. This method of using image style transfer has achieved better results than the CNN models without domain adaptation, but the regression error in the background area reduces counting performance.…”

“…To make our adapted model can extract the semantic consistency feature for synthetic and realworld data, we first introduce a semantic extractor by further exploiting the semantic label. Considering that GCC [16] dataset provides the mask for crowd area, correspondingly, we train a segmentation model and get the semantic label for real datasets in free. Furthermore, we adopt adversarial learning to align the semantic space.…”