Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting

• URL: http://arxiv.org/abs/2205.14659v1
• Date: Sun, 29 May 2022 13:39:34 GMT
• Title: Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting
• Authors: Zheng Xiong, Liangyu Chai, Wenxi Liu, Yongtuo Liu, Sucheng Ren and Shengfeng He
• Abstract summary: Crowd image is arguably one of the most laborious data to annotate. We propose a novel weakly-supervised setting, in which we leverage the binary ranking of two images with high-contrast crowd counts as training guidance. We conduct extensive experiments to study various combinations of supervision, and we show that the proposed method outperforms existing weakly-supervised methods by a large margin.
• Score: 43.446730359817515
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model [60.30099369475092]
  Supervised crowd counting relies heavily on costly manual labeling. We propose a novel unsupervised framework for crowd counting, named CrowdCLIP. CrowdCLIP achieves superior performance compared to previous unsupervised state-of-the-art counting methods.
  arXiv  Detail & Related papers  (2023-04-09T12:56:54Z)
• Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting [48.15210212256114]
  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.
  arXiv  Detail & Related papers  (2022-01-13T07:25:06Z)
• Completely Self-Supervised Crowd Counting via Distribution Matching [92.09218454377395]
  We propose a complete self-supervision approach to training models for dense crowd counting. The only input required to train, apart from a large set of unlabeled crowd images, is the approximate upper limit of the crowd count. Our method dwells on the idea that natural crowds follow a power law distribution, which could be leveraged to yield error signals for backpropagation.
  arXiv  Detail & Related papers  (2020-09-14T13:20:12Z)
• Fine-Grained Crowd Counting [59.63412475367119]
  Current crowd counting algorithms are only concerned with the number of people in an image. We propose fine-grained crowd counting, which differentiates a crowd into categories based on the low-level behavior attributes of the individuals.
  arXiv  Detail & Related papers  (2020-07-13T01:31:12Z)
• Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks [50.78037828213118]
  This paper tackles the semi-supervised crowd counting problem from the perspective of feature learning. We propose a novel semi-supervised crowd counting method which is built upon two innovative components.
  arXiv  Detail & Related papers  (2020-07-07T05:30:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.