3 papers
cs.LG2018
Yes, IoU loss is submodular - as a function of the mispredictions
Maxim Berman, Matthew B. Blaschko, Amal Rannen Triki +1
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 t…
cs.CV2017
An Efficient Decomposition Framework for Discriminative Segmentation with Supermodular Losses
Jiaqian Yu, Matthew B. Blaschko
Several supermodular losses have been shown to improve the perceptual quality of image segmentation in a discriminative framework such as a structured output support vector machine…
stat.ML2016
A Convex Surrogate Operator for General Non-Modular Loss Functions
Jiaqian Yu, Matthew Blaschko
Empirical risk minimization frequently employs convex surrogates to underlying discrete loss functions in order to achieve computational tractability during optimization. However,…