# Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer

arXiv: https://arxiv.org/abs/2008.05383 · HTML: https://mlsanity.com/paper/2008.05383/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2020.

## Built on by (most cited first, 13 of 13)

- [Domain-General Crowd Counting in Unseen Scenarios](https://mlsanity.com/paper/2212.02573/) (2022)
- [Redesigning Multi-Scale Neural Network for Crowd Counting](https://mlsanity.com/paper/2208.02894/) (2022)
- [Single Domain Generalization for Crowd Counting](https://mlsanity.com/paper/2403.09124/) (2024)
- [DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting](https://mlsanity.com/paper/2308.05311/) (2023)
- [Self-supervised Domain Adaptation in Crowd Counting](https://mlsanity.com/paper/2206.03431/) (2022)
- [Single Domain Generalization for Few-Shot Counting via Universal Representation Matching](https://mlsanity.com/paper/2505.16778/) (2025)
- [Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting](https://mlsanity.com/paper/2505.21943/) (2025)
- [Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2503.17984/) (2025)
- [Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation](https://mlsanity.com/paper/2108.02980/) (2021)
- [L2HCount:Generalizing Crowd Counting from Low to High Crowd Density via Density Simulation](https://mlsanity.com/paper/2503.12935/) (2025)
- [TCFormer: A 5M-Parameter Transformer with Density-Guided Aggregation for Weakly-Supervised Crowd Counting](https://mlsanity.com/paper/2512.22203/) (2025)
- [Towards Conditional Feature Alignment for Cross-Domain Counting](https://mlsanity.com/paper/2506.17137/) (2025)
- [Granular Ball Guided Stable Latent Domain Discovery for Domain-General Crowd Counting](https://mlsanity.com/paper/2603.24106/) (2026)

## Abstract (arXiv)

Unsupervised crowd counting is a challenging yet not largely explored task. In this paper, we explore it in a transfer learning setting where we learn to detect and count persons in an unlabeled target set by transferring bi-knowledge learnt from regression- and detection-based models in a labeled source set. The dual source knowledge of the two models is heterogeneous and complementary as they capture different modalities of the crowd distribution. We formulate the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge distillation between the two models. Given the regression- and detection-based models and their mutual transformers learnt in the source, we introduce an iterative self-supervised learning scheme with regression-detection bi-knowledge transfer in the target. Extensive experiments on standard crowd counting benchmarks, ShanghaiTech, UCFCC50, and UCFQNRF demonstrate a substantial improvement of our method over other state-of-the-arts in the transfer learning setting.