Research map / Label-efficient and robust learning / Noisy labels
Counting without Scale: Scale-Consistent Error Correction for Crowd Counting
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a scale-aware invariance approach for crowd counting that aims to correct noisy annotations and keep counts consistent across image scales.
Problem
Crowd counting must stay scale-invariant despite noisy human labels, and existing methods lose consistency and robustness when test images differ in scale from training data.
Approach
Scale-consistent error correction for counting, framed around scale-aware invariance to handle noisy labels and scale shift between train and test images; the abstract is truncated so the specific mechanism is not stated.
Closest papers by meaning
- Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (CVPR 2018 · similarity 0.90)
- To Choose or to Fuse? Scale Selection for Crowd Counting (AAAI 2021 · similarity 0.90)
- Free Lunch Enhancements for Multi-modal Crowd Counting (CVPR 2025 · similarity 0.88)
- Single Domain Generalization for Crowd Counting (CVPR 2024 · similarity 0.88)
- Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting (CVPR 2025 · similarity 0.87)
- Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting (CVPR 2025 · similarity 0.87)
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.