Weakly-supervised multi-class object localization using only object counts as labels

02/23/2021
by   Kyle Mills, et al.
14

We demonstrate the use of an extensive deep neural network to localize instances of objects in images. The EDNN is naturally able to accurately perform multi-class counting using only ground truth count values as labels. Without providing any conceptual information, object annotations, or pixel segmentation information, the neural network is able to formulate its own conceptual representation of the items in the image. Using images labelled with only the counts of the objects present,the structure of the extensive deep neural network can be exploited to perform localization of the objects within the visual field. We demonstrate that a trained EDNN can be used to count objects in images much larger than those on which it was trained. In order to demonstrate our technique, we introduce seven new data sets: five progressively harder MNIST digit-counting data sets, and two datasets of 3d-rendered rubber ducks in various situations. On most of these datasets, the EDNN achieves greater than 99

READ FULL TEXT

page 3

page 5

page 6

page 8

research
07/15/2023

Learning from Pseudo-labeled Segmentation for Multi-Class Object Counting

Class-agnostic counting (CAC) has numerous potential applications across...
research
05/29/2015

Learning to count with deep object features

Learning to count is a learning strategy that has been recently proposed...
research
07/03/2020

A Few-Shot Sequential Approach for Object Counting

In this work, we address the problem of few-shot multi-classobject count...
research
04/01/2018

Robust Fruit Counting: Combining Deep Learning, Tracking, and Structure from Motion

We present a novel fruit counting pipeline that combines deep segmentati...
research
08/05/2020

A Robot that Counts Like a Child – a Developmental Model of Counting and Pointing

In this paper, a novel neuro-robotics model capable of counting real ite...
research
02/07/2019

StampNet: unsupervised multi-class object discovery

Unsupervised object discovery in images involves uncovering recurring pa...
research
12/08/2015

Learning to Point and Count

This paper proposes the problem of point-and-count as a test case to bre...

Please sign up or login with your details

Forgot password? Click here to reset