From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting

01/07/2020
by   Haipeng Xiong, et al.
20

Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i.e., the number of population can vary in [0, inf) in theory. However, collected data and labeled instances are limited in reality, which means that only a small closed set is observed. Existing methods typically model this task in a regression manner, while they are prone to suffer from an unseen scene with counts out of the scope of the closed set. In fact, counting has an interesting and exclusive property—spatially decomposable. A dense region can always be divided until sub-region counts are within the previously observed closed set. We therefore introduce the idea of spatial divide-and-conquer (S-DC) that transforms open-set counting into a closed-set problem. This idea is implemented by a novel Supervised Spatial Divide-and-Conquer Network (SS-DCNet). Thus, SS-DCNet can only learn from a closed set but generalize well to open-set scenarios via S-DC. SS-DCNet is also efficient. To avoid repeatedly computing sub-region convolutional features, S-DC is executed on the feature map instead of on the input image. We provide theoretical analyses as well as a controlled experiment on toy data, demonstrating why closed-set modeling makes sense. Extensive experiments show that SS-DCNet achieves the state-of-the-art performance. Code and models are available at: https://tinyurl.com/SS-DCNet.

READ FULL TEXT

page 1

page 2

page 5

page 8

page 11

page 13

page 15

research
08/15/2019

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

Visual counting, a task that predicts the number of objects from an imag...
research
07/20/2022

Discrete-Constrained Regression for Local Counting Models

Local counts, or the number of objects in a local area, is a continuous ...
research
05/08/2020

Introduction of a new Dataset and Method for Detecting and Counting the Pistachios based on Deep Learning

Pistachio is a nutritious nut that has many uses in the food industry. I...
research
04/12/2016

Counting Everyday Objects in Everyday Scenes

We are interested in counting the number of instances of object classes ...
research
05/24/2023

DC-Net: Divide-and-Conquer for Salient Object Detection

In this paper, we introduce Divide-and-Conquer into the salient object d...
research
03/25/2019

CODA: Counting Objects via Scale-aware Adversarial Density Adaption

Recent advances in crowd counting have achieved promising results with i...
research
06/03/2019

Automated Steel Bar Counting and Center Localization with Convolutional Neural Networks

Automated steel bar counting and center localization plays an important ...

Please sign up or login with your details

Forgot password? Click here to reset