Weighing Counts: Sequential Crowd Counting by Reinforcement Learning
Files
(Accepted version)
Date
2020
Authors
Liu, L.
Lu, H.
Zou, H.
Xiong, H.
Cao, Z.
Shen, C.
Editors
Bischof, H.
Brox, T.
Vedaldi, A.
Frahm, J.M.
Brox, T.
Vedaldi, A.
Frahm, J.M.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Lecture Notes in Artificial Intelligence, 2020 / Bischof, H., Brox, T., Vedaldi, A., Frahm, J.M. (ed./s), vol.12355, pp.164-181
Statement of Responsibility
Liang Liu, Hao Lu, Hongwei Zou, Haipeng Xiong, Zhiguo Cao, and Chunhua Shen
Conference Name
European Conference on Computer Vision (ECCV) (23 Aug 2020 - 28 Aug 2020 : virtual online)
Abstract
We formulate counting as a sequential decision problem and present a novel crowd counting model solvable by deep reinforcement learning. In contrast to existing counting models that directly output count values, we divide one-step estimation into a sequence of much easier and more tractable sub-decision problems. Such sequential decision nature corresponds exactly to a physical process in reality—scale weighing. Inspired by scale weighing, we propose a novel ‘counting scale’ termed LibraNet where the count value is analogized by weight. By virtually placing a crowd image on one side of a scale, LibraNet (agent) sequentially learns to place appropriate weights on the other side to match the crowd count. At each step, LibraNet chooses one weight (action) from the weight box (the pre-defined action pool) according to the current crowd image features and weights placed on the scale pan (state). LibraNet is required to learn to balance the scale according to the feedback of the needle (Q values). We show that LibraNet exactly implements scale weighing by visualizing the decision process how LibraNet chooses actions. Extensive experiments demonstrate the effectiveness of our design choices and report stateof- the-art results on a few crowd counting benchmarks, including ShanghaiTech, UCF CC 50 and UCF-QNRF. We also demonstrate good crossdataset generalization of LibraNet. Code and models are made available at https://git.io/libranet.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© Springer Nature Switzerland AG 2020