Domain-Adaptive Crowd Counting via High-Quality Image Translation and Density Reconstruction

• Published in: IEEE transaction on neural networks and learning systems Vol. 34; no. 8; pp. 4803 - 4815
• Main Authors: Gao, Junyu, Han, Tao, Yuan, Yuan, Wang, Qi
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Convolutional neural networks; Crowd counting; Decoding; Density; domain adaptation; Feature extraction; Head; Image processing; Image quality; Image reconstruction; Image segmentation; image translation; Labels; Reconstruction; Supervised learning; Synthetic data; Task analysis; Translation
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2021.3124272

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 article 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.