mlsanityData to 7 Oct 2026

Enhanced Information Fusion Network for Crowd Counting

arXiv 2101.04279 ↗First posted 12 Jan 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In recent years, crowd counting, a technique for predicting the number of people in an image, becomes a challenging task in computer vision. In this paper, we propose a cross-column feature fusion network to solve the problem of information redundancy in columns. We introduce the Information Fusion Module (IFM) which provides a channel for information flow to help different columns to obtain significant information from another column. Through this channel, different columns exchange information with each other and extract useful features from the other column to enhance key information. Hence, there is no need for columns to pay attention to all areas in the image. Each column can be responsible for different regions, thereby reducing the burden of each column. In experiments, the generalizability of our model is more robust and the results of transferring between different datasets acheive the comparable results with the state-of-the-art models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 36 references that are in the map. First posted on arXiv 12 Jan 2021.

Builds on

21 of 36 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  4. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  5. 2019Real-time Scene Text Detection with Differentiable Binarizationcited by 212
  6. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  7. 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
  8. 2017Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNscited by 55
  9. 2016CrowdNet: A Deep Convolutional Network for Dense Crowd Countingcited by 52
  10. 2017DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimationcited by 49
  11. 2019Crowd Counting with Deep Structured Scale Integration Networkcited by 46
  12. 2018ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understandingcited by 45
9 more
  1. 2017CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Countingcited by 41
  2. 2019Learning Spatial Awareness to Improve Crowd Countingcited by 36
  3. 2019Counting with Focus for Freecited by 33
  4. 2019Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Countingcited by 32
  5. 2019C^3 Framework: An Open-source PyTorch Code for Crowd Countingcited by 18
  6. 2019Improving the Learning of Multi-column Convolutional Neural Network for Crowd Countingcited by 15
  7. 2019Crowd Counting on Images with Scale Variation and Isolated Clusterscited by 4
  8. 2017ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classificationcited by 3
  9. 2019Inverse Attention Guided Deep Crowd Counting Networkcited by 3

Built on by

Not cited yet.