Learning Discriminative Features for Crowd Counting
- 7 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 33 (10577149) , 3749-3764
Abstract
Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations. The reason is that objects in highly congested areas are normally small and high-level features extracted by convolutional neural networks are less discriminative to represent small objects. To address these problems, we propose a learning discriminative features framework for crowd counting, which is composed of a masked feature prediction module (MPM) and a supervised pixel-level contrastive learning module (CLM). The MPM randomly masks feature vectors in the feature map and then reconstructs them, allowing the model to learn about what is present in the masked regions and improving the model’s ability to localize objects in high-density regions. The CLM pulls targets close to each other and pushes them far away from background in the feature space, enabling the model to discriminate foreground objects from background. Additionally, the proposed modules can be beneficial in various computer vision tasks, such as crowd counting and object detection, where dense scenes or cluttered environments pose challenges to accurate localization. The proposed two modules are plug-and-play, incorporating the proposed modules into existing models can potentially boost their performance in these scenarios.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62073257)
- Key Research and Development Program of Shaanxi Province of China (62073257)
This publication has 76 references indexed in Scilit:
- An End-to-End Transformer Model for Crowd Localization2022
- MultiMAE: Multi-modal Multi-task Masked Autoencoders2022
- TransCrowd: weakly-supervised crowd counting with transformersScience China Information Sciences, 2022
- AutoScale: Learning to Scale for Crowd CountingInternational Journal of Computer Vision, 2022
- Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds2018
- Where Are the Blobs: Counting by Localization with Point Supervision2018
- Scale Aggregation Network for Accurate and Efficient Crowd Counting2018
- Densely Connected Convolutional Networks2017
- Finding Tiny Faces2017
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network2016