Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting

Abstract

Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4,000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are available at https://github.com/bridgeqiqi/DREAM.

Accepted by IEEE Transactions on Neural Networks and Learning Systems

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
• MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
• CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
• PaDNet: Pan-Density Crowd Counting
• Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting
• Cross-head Supervision for Crowd Counting with Noisy Annotations
• Motion Matters: A Novel Motion Modeling For Cross-View Gait Feature Learning
• Image Quality Assessment: Learning to Rank Image Distortion Level
• Confidence Estimation Using Unlabeled Data