Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting
This addresses the labor-intensive annotation problem in crowd counting for computer vision applications, but it is incremental as it builds on existing weakly-supervised methods.
The paper tackles the problem of reducing annotation effort for crowd counting by introducing a weakly-supervised setting that uses binary ranking labels of images with high-contrast counts, converting regression to ranking potential prediction. It shows that the method outperforms existing weakly-supervised approaches by a large margin, though specific numbers are not provided in the abstract.
Crowd image is arguably one of the most laborious data to annotate. In this paper, we devote to reduce the massive demand of densely labeled crowd data, and propose a novel weakly-supervised setting, in which we leverage the binary ranking of two images with high-contrast crowd counts as training guidance. To enable training under this new setting, we convert the crowd count regression problem to a ranking potential prediction problem. In particular, we tailor a Siamese Ranking Network that predicts the potential scores of two images indicating the ordering of the counts. Hence, the ultimate goal is to assign appropriate potentials for all the crowd images to ensure their orderings obey the ranking labels. On the other hand, potentials reveal the relative crowd sizes but cannot yield an exact crowd count. We resolve this problem by introducing "anchors" during the inference stage. Concretely, anchors are a few images with count labels used for referencing the corresponding counts from potential scores by a simple linear mapping function. We conduct extensive experiments to study various combinations of supervision, and we show that the proposed method outperforms existing weakly-supervised methods without additional labeling effort by a large margin.