Official Implementation of ACMMM'21 paper "Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting"
We recommend to divide the entire range of counts into strata to later sample images from these strata. The procedure for data split generation is provided in the folder named binning
.
We explored two methods of sampling images from strata.
- Round Robin sampling
- Random sampling
For a simple visualisation of the procedure you can refer to the folder named sampling
.
To reduce variance, we adopt a strata-aware optimization. A pyTorch implementation of that optimization is provided in this folder named optimization
.
We evaluate the performance at a strata-level (mean and std) and a pooled mean and std. The folder evaluation
consists of a notebook to do the same.
Cite us:
@inproceedings{10.1145/3474085.3475522,
author = {Sravya Vardhani Shivapuja, Mansi Pradeep Khamkar, Divij Bajaj, Ganesh Ramakrishnan, Ravi Kiran Sarvadevabhatla},
title = {Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm
for Crowd Counting
},
booktitle = {Proceedings of the 2021 ACM Conference on Multimedia},
year = {2021},
location = {Virtual Event, China},
publisher = {ACM},
address = {China},
}