Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting

Abstract

Fully-supervised crowd counting is a laborious task due to the large amounts of annotations. Few works focus on weekly-supervised crowd counting, where only the global crowd numbers are available for training. The main challenge of weekly-supervised crowd counting is the lack of local supervision information. To address this problem, we propose a self-adaptive feature similarity learning (SFSL) network and a global-local consistency (GLC) loss to reinforce local feature representation. We introduce a feature vector which represents the unbiased feature estimation of persons. The network updates the feature vector self-adaptively and utilizes the feature similarity for the regression of crowd numbers. Besides, the proposed GLC loss leverages the consistency between the network estimations from global and local areas. The experimental results demonstrate that our proposed method based on different backbones narrows the gap between weakly-supervised and fully-supervised dense crowd counting.

RGB-T Multi-Modal Crowd Counting Based on Transformer

“…It constructs a weakly supervised model from sequence-to-count perspective. SFSL [5] introduces a learnable unbiased feature estimation of persons and utilizes the feature similarity for the regression of crowd numbers to solve the lack of local supervision. CrowdMLP [37] proposes a multi-granularity multilayer perceptron (MLP) regressor to enlarge receptive fields and a split-counting to decouple spatial constraints.…”