Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction

Abstract

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.

Accepted by IEEE T-NNLS

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Transferable Features with Deep Adaptation Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Separation Networks
• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
• Fully Convolutional Neural Networks for Crowd Segmentation
• Generalizing semi-supervised generative adversarial networks to regression using feature contrasting
• C^3 Framework: An Open-source PyTorch Code for Crowd Counting