Object Counting with Small Datasets of Large Images

05/28/2018
by   Shubhra Aich, et al.
0

We explore the problem of training one-look regression models for counting objects in datasets comprising a small number of high-resolution, variable-shaped images. To reduce overfitting when training on full resolution samples, we propose to use global sum pooling (GSP) instead of global average pooling (GAP) or fully connected (FC) layers at the backend of a convolutional neural network. Although computationally equivalent to GAP, we show via detailed experimentation that GSP allows convolutional networks to learn the counting task as a simple linear mapping problem generalized over the input shape and the number of objects present. We evaluate our approach on four different aerial image datasets - three car counting datasets (CARPK, PUCPR+, and COWC) and one new challenging dataset for wheat spike counting. Our GSP approach achieves state-of-the-art performance on all four datasets and GSP models trained with smaller-sized image patches localize objects better than their GAP counterparts.

READ FULL TEXT

page 2

page 4

page 6

page 7

page 8

research
02/08/2021

Counting and Locating High-Density Objects Using Convolutional Neural Network

This paper presents a Convolutional Neural Network (CNN) approach for co...
research
03/14/2018

Improving Object Counting with Heatmap Regulation

In this paper, we propose a simple and effective way to improve one-look...
research
08/24/2017

Leaf Counting with Deep Convolutional and Deconvolutional Networks

In this paper, we investigate the problem of counting rosette leaves fro...
research
04/23/2023

Indiscernible Object Counting in Underwater Scenes

Recently, indiscernible scene understanding has attracted a lot of atten...
research
04/20/2018

An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting

We propose the use of dilated filters to construct an aggregation module...
research
07/22/2018

A Statistical Method for Object Counting

In this paper we present a new object counting method that is intended f...
research
04/14/2020

Exploring Cell counting with Neural Arithmetic Logic Units

The big problem for neural network models which are trained to count ins...

Please sign up or login with your details

Forgot password? Click here to reset