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

Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN

Sam, Deepak Babu and Sajjan, Neeraj N and Babu, R Venkatesh and Srinivasan, Mukundhan (2018) Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN. In: 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), JUN 18-23, 2018, Salt Lake City, UT, pp. 3618-3626.

[img] PDF
Iee_Cvf_Con_Vis_Pat_Rec_CVPR_3618_2018.pdf - Published Version
Restricted to Registered users only

Download (388kB) | Request a copy
Official URL: https://doi.org/10.1109/CVPR.2018.00381

Abstract

Automated counting of people in crowd images is a challenging task. The major difficulty stems from the large diversity in the way people appear in crowds. In fact, features available for crowd discrimination largely depend on the crowd density to the extent that people are only seen as blobs in a highly dense scene. We tackle this problem with a growing CNN which can progressively increase its capacity to account for the wide variability seen in crowd scenes. Our model starts from a base CNN density regressor, which is trained in equivalence on all types of crowd images. In order to adapt with the huge diversity, we create two child regressors which are exact copies of the base CNN. A differential training procedure divides the dataset into two clusters and fine-tunes the child networks on their respective specialties. Consequently, without any hand-crafted criteria for forming specialties, the child regressors become experts on certain types of crowds. The child networks are again split recursively, creating two experts at every division. This hierarchical training leads to a CNN tree, where the child regressors are more fine experts than any of their parents. The leaf nodes are taken as the final experts and a classifier network is then trained to predict the correct specialty for a given test image patch. The proposed model achieves higher count accuracy on major crowd datasets. Further, we analyse the characteristics of specialties mined automatically by our method.

Item Type: Conference Paper
Additional Information: 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, JUN 18-23, 2018
Department/Centre: Division of Interdisciplinary Research > Computational and Data Sciences
Depositing User: Id for Latest eprints
Date Deposited: 27 Feb 2019 09:28
Last Modified: 27 Feb 2019 09:28
URI: http://eprints.iisc.ac.in/id/eprint/61851

Actions (login required)

View Item View Item