Research map / Label-efficient and robust learning / Domain adaptation and generalization
CD-CNN: A Partially Supervised Cross-Domain Deep Learning Model for Urban Resident Recognition
Jingyuan Wang, Xu He, Ze Wang, Junjie Wu, Nicholas Jing Yuan, Xing Xie, Zhang Xiong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the full cross-domain CNN with dimensionality balancing and co-training instead of the evaluated benchmarks | Resident recognition from Wuxi mobile signaling data · Wuxi | precision, recall, and F1-score | Improved |
| Remove the dimensionality balancing subnetwork (ablation) | CD-CNN · Wuxi resident recognition | classification performance | Hurt |
| Add dimensionality balancing for location and communication features (ablation) | CD-CNN · Wuxi resident recognition | classification performance | Improved |
| Remove the co-training step and use only labeled samples (ablation) | CD-CNN · Wuxi resident recognition | classification performance | Hurt |
| Replace the CNN structure with Stacked Auto-Encoders (ablation) | CD-CNN · Wuxi resident recognition | classification performance | Hurt |
| Increase the number of data-collecting days | CD-CNN · Wuxi resident recognition | classification performance | Improved |
| Collect data for longer than 15 days | CD-CNN · Wuxi resident recognition | marginal performance benefit | No clear effect |
| Reduce the number of labeled training samples | CD-CNN · Wuxi resident recognition | classification performance | Mixed |
| Increase migrant-confidence bin | CD-CNN migrant-confidence predictions · Spring Festival 2014 hometown-returning prediction | leaving rate: 0.16 -> 0.32 -> 0.51 -> 0.71 -> 0.94 | Improved |
Closest papers by meaning
- MobileODE: An Extra Lightweight Network (NeurIPS 2025 · similarity 0.82)
- Deep Learning the City: Quantifying Urban Perception at a Global Scale (ECCV 2016 · similarity 0.82)
- MnasNet: Platform-Aware Neural Architecture Search for Mobile (CVPR 2019 · similarity 0.81)
- Diffusion Transformers as Open-World Spatiotemporal Foundation Models (NeurIPS 2025 · similarity 0.79)
- Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification (NeurIPS 2025 · similarity 0.79)
- UrbanDataLayer: A Unified Data Pipeline for Urban Science (NeurIPS 2024 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
