Yes, IoU loss is submodular - as a function of the mispredictions

09/06/2018
by   Maxim Berman, et al.
0

This note is a response to [7] in which it is claimed that [13, Proposition 11] is false. We demonstrate here that this assertion in [7] is false, and is based on a misreading of the notion of set membership in [13, Proposition 11]. We maintain that [13, Proposition 11] is true. ([7] = arXiv:1809.00593, [13] = arXiv:1512.07797)

READ FULL TEXT

page 1

page 2

page 3

research
12/31/2019

True and false discoveries with e-values

We discuss controlling the number of false discoveries using e-values in...
research
09/02/2020

A Heaviside Function Approximation for Neural Network Binary Classification

Neural network binary classifiers are often evaluated on metrics like ac...
research
03/29/2021

A Note on Isolating Cut Lemma for Submodular Function Minimization

It has been observed independently by many researchers that the isolatin...
research
12/31/2019

Submodular Function Minimization and Polarity

Using polarity, we give an outer polyhedral approximation for the epigra...
research
02/16/2018

Detecting truth on components

We investigate and generalize to an extended framework the notion of 'tr...
research
07/11/2022

Submodular Dominance and Applications

In submodular optimization we often deal with the expected value of a su...
research
09/26/2019

Adaptive Class Weight based Dual Focal Loss for Improved Semantic Segmentation

In this paper, we propose a Dual Focal Loss (DFL) function, as a replace...

Please sign up or login with your details

Forgot password? Click here to reset