mlsanityData to 14 Oct 2026

Progressive Multi-resolution Loss for Crowd Counting

arXiv 2212.04127 ↗First posted 8 Dec 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Crowd counting is usually handled in a density map regression fashion, which is supervised via a L2 loss between the predicted density map and ground truth. To effectively regulate models, various improved L2 loss functions have been proposed to find a better correspondence between predicted density and annotation positions. In this paper, we propose to predict the density map at one resolution but measure the density map at multiple resolutions. By maximizing the posterior probability in such a setting, we obtain a log-formed multi-resolution L2-difference loss, where the traditional single-resolution L2 loss is its particular case. We mathematically prove it is superior to a single-resolution L2 loss. Without bells and whistles, the proposed loss substantially improves several baselines and performs favorably compared to state-of-the-art methods on four crowd counting datasets, ShanghaiTech A & B, UCF-QNRF, and JHU-Crowd++.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 31 of its 58 references that are in the map. First posted on arXiv 8 Dec 2022.

Builds on

31 of 58 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  7. 2018Computational Optimal Transportcited by 780
  8. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  9. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  10. 2019Bayesian Loss for Crowd Count Estimation with Point Supervisioncited by 162
  11. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  12. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
19 more
  1. 2018Context-Aware Crowd Countingcited by 150
  2. 2019Learning from Synthetic Data for Crowd Counting in the Wildcited by 148
  3. 2020Distribution Matching for Crowd Countingcited by 143
  4. 2020JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Methodcited by 109
  5. 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
  6. 2022An End-to-End Transformer Model for Crowd Localizationcited by 74
  7. 2019Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detectioncited by 73
  8. 2018Leveraging Unlabeled Data for Crowd Counting by Learning to Rankcited by 57
  9. 2022Rethinking Spatial Invariance of Convolutional Networks for Object Countingcited by 54
  10. 2019From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquercited by 48
  11. 2019Crowd Counting with Deep Structured Scale Integration Networkcited by 46
  12. 2019Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Countingcited by 36
  13. 2021Focal Inverse Distance Transform Maps for Crowd Localizationcited by 36
  14. 2019AutoScale: Learning to Scale for Crowd Counting and Localizationcited by 35
  15. 2019SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Countingcited by 28
  16. 2020Adaptive Mixture Regression Network with Local Counting Map for Crowd Countingcited by 28
  17. 2022Semi-supervised Crowd Counting via Density Agencycited by 18
  18. 2022Redesigning Multi-Scale Neural Network for Crowd Countingcited by 17
  19. 2022Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimationcited by 8

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2023Semi-Supervised Crowd Counting with Contextual Modeling: Facilitating Holistic Understanding of Crowd Scenescited by 6
  2. 2024The Effectiveness of a Simplified Model Structure for Crowd Countingcited by 3
  3. 2025Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encodingcited by 1
  4. 2023Remote Sensing Object Counting with Online Knowledge Learningcited by 0