Zhiping Shi
Paper download is intended for registered attendees only, and is
subjected to the IEEE Copyright Policy. Any other use is strongly forbidden.
Papers from this author
DAPC: Domain Adaptation People Counting Via Style-Level Transfer Learning and Scene-Aware Estimation
Na Jiang, Xingsen Wen, Zhiping Shi
Auto-TLDR; Domain Adaptation People counting via Style-Level Transfer Learning and Scene-Aware Estimation
Abstract Slides Poster Similar
People counting concentrates on predicting the number of people in surveillance images. It remains challenging due to the rich variations in scene type and crowd density. Besides, the limited closed-set with ground truth from reality significantly increase the difficulty of people counting in actual open-set. Targeting to solve these problems, this paper proposes a domain adaptation people counting via style-level transfer learning (STL) and scene-aware estimation (SAE). The style-level transfer learning explicitly leverages the style constraint and content similarity between images to learn effective knowledge transfer, which narrows the gap between closed-set and open-set by generating domain adaptation images. The scene-aware estimation introduces scene classifier to provide scene-aware weights for adaptively fusing density maps, which alleviates interference of variations in scene type and crowd density on domain adaptation people counting. Extensive experimental results demonstrate that images generated by STL are more suitable for domain adaptation learning and our proposed approach significantly outperforms the state-of-the-art methods on multiple cross-domain pairs.