Research map / Label-efficient and robust learning / Domain adaptation and generalization
Explicit Invariant Feature Induced Cross-Domain Crowd Counting
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 IF-CKT+ instead of CDCC | cross-domain crowd counting · ShanghaiTech B | MAE: 11.4 -> 10.9 | Helped |
| use IF-CKT+ instead of CDCC | cross-domain crowd counting · WorldExpo’10 Avg. | MAE: 16.6 -> 16.4 | Helped |
| use IF-CKT+ instead of CDCC | cross-domain crowd counting · UCF-QNRF | MAE: 198.3 -> 190.6 | Helped |
| use IF-CKT+ instead of FSC | cross-domain crowd counting · MALL | MAE: 2.47 -> 2.14 | Helped |
| add GFD feature decoupling (ablation) | IF-CKT on GCC to UCF-QNRF · UCF-QNRF | MAE: 275.4 -> 225.3 | Helped |
| add relation exploration (ablation) | IF-CKT on GCC to UCF-QNRF · UCF-QNRF | MAE: 225.3 -> 209.7 | Helped |
| add bridge loss (ablation) | IF-CKT on GCC to UCF-QNRF · UCF-QNRF | MAE: 209.7 -> 200.4 | Helped |
| rank target images and separate high- and low-confidence pseudo-labels (ablation) | IF-CKT GKE on GCC to UCF-QNRF · UCF-QNRF | MAE: 200.4 -> 190.6 | Helped |
| set λ to 0.74 rather than 0 (ablation) | IF-CKT+ · UCF-QNRF | MAE: 198.7 -> 190.6 | Helped |
| increase graph node count from 2 to 3 (ablation) | IF-CKT+ · ShanghaiTech B | MAE: 12.3 to 10.9 | Helped |
| increase graph node count from 3 to 5 (ablation) | IF-CKT+ · ShanghaiTech B | MAE: 10.9 to 10.9 | No clear effect |
| increase message-passing iterations from 1 to 3 (ablation) | IF-CKT+ · ShanghaiTech B | MAE: 13.1 to 10.9 | Helped |
Closest papers by meaning
- Domain-General Crowd Counting in Unseen Scenarios (AAAI 2023 · similarity 0.91)
- Error-Aware Density Isomorphism Reconstruction for Unsupervised Cross-Domain Crowd Counting (AAAI 2021 · similarity 0.90)
- Single Domain Generalization for Crowd Counting (CVPR 2024 · similarity 0.87)
- Free Lunch Enhancements for Multi-modal Crowd Counting (CVPR 2025 · similarity 0.87)
- Gramformer: Learning Crowd Counting via Graph-Modulated Transformer (AAAI 2024 · similarity 0.85)
- Graph-Based Cross-Domain Knowledge Distillation for Cross-Dataset Text-to-Image Person Retrieval (AAAI 2025 · similarity 0.84)
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.