ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Almost unsupervised learning for dense crowd counting

Sam, DB and Sajjan, NN and Maurya, H and Venkatesh Babu, R (2019) Almost unsupervised learning for dense crowd counting. In: 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Annual Conference on Innovative Applications of Artificial Intelligence, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, 27 January 2019through 1 February 2019, Honolulu, pp. 8868-8875.

[img] PDF
EAAI_2019.pdf - Published Version
Restricted to Registered users only

Download (4MB) | Request a copy
Official URL: https://doi.org/10.1609/aaai.v33i01.33018868

Abstract

We present an unsupervised learning method for dense crowd count estimation. Marred by large variability in appearance of people and extreme overlap in crowds, enumerating people proves to be a difficult task even for humans. This implies creating large-scale annotated crowd data is expensive and directly takes a toll on the performance of existing CNN based counting models on account of small datasets. Motivated by these challenges, we develop Grid Winner-Take-All (GWTA) autoencoder to learn several layers of useful filters from unlabeled crowd images. Our GWTA approach divides a convolution layer spatially into a grid of cells. Within each cell, only the maximally activated neuron is allowed to update the filter. Almost 99.9 of the parameters of the proposed model are trained without any labeled data while the rest 0.1 are tuned with supervision. The model achieves superior results compared to other unsupervised methods and stays reasonably close to the accuracy of supervised baseline. Furthermore, we present comparisons and analyses regarding the quality of learned features across various models.

Item Type: Conference Paper
Publication: 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, 31st Innovative Applications of Artificial Intelligence Conference, IAAI 2019 and the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019
Publisher: AAAI Press
Additional Information: The copyright for this article belongs to AAAI Press.
Keywords: Large dataset; Unsupervised learning, Auto encoders; Count estimation; Counting models; Grid of cells; Small data set; Unsupervised learning method; Unsupervised method; Winner take alls, Learning systems
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Others
Date Deposited: 02 Dec 2022 09:47
Last Modified: 02 Dec 2022 09:47
URI: https://eprints.iisc.ac.in/id/eprint/78181

Actions (login required)

View Item View Item