Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction
This work addresses the need for reducing manual labeling in crowd counting by enabling effective transfer from synthetic to real data, though it is incremental as it builds on existing domain adaptation methods.
The paper tackles the problem of domain adaptation for crowd counting by proposing a framework that translates synthetic images to realistic ones and reconstructs density maps, achieving state-of-the-art performance on six real-world datasets.
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 proposes a Domain-Adaptive Crowd Counting (DACC) framework, which consists of a high-quality image translation and density map reconstruction. To be specific, the former focuses on translating synthetic data to realistic images, which prompts the translation quality by segregating domain-shared/independent features and designing content-aware consistency loss. The latter aims at generating pseudo labels on real scenes to improve the prediction quality. 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.