The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses

The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses

24 December 2015

Matthew Blaschko

Papers citing "The Lovász Hinge: A Novel Convex Surrogate for Submodular Losses"

8 / 8 papers shown

Title
Structured Prediction with Abstention via the Lovász Hinge Jessie Finocchiaro Rafael Frongillo Enrique Nueve 29 0 0 09 May 2025
Trading off Consistency and Dimensionality of Convex Surrogates for the Mode Enrique Nueve Bo Waggoner Dhamma Kimpara Jessie Finocchiaro 44 1 0 16 Feb 2024
Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels Zifu Wang Xuefei Ning Matthew B. Blaschko VLM 35 12 0 11 Feb 2023
UNet#: A UNet-like Redesigning Skip Connections for Medical Image Segmentation Ledan Qian Xiao Zhou Yi Li Zhongyi Hu 44 5 0 24 May 2022
The Structured Abstain Problem and the Lovász Hinge Jessie Finocchiaro Rafael Frongillo Enrique Nueve 22 3 0 16 Mar 2022
Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index Tom Eelbode J. Bertels Maxim Berman Dirk Vandermeulen F. Maes R. Bisschops Matthew B. Blaschko 30 255 0 26 Oct 2020
Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models Vincent Le Guen Nicolas Thome AI4TS 32 134 0 19 Sep 2019
Yes, IoU loss is submodular - as a function of the mispredictions Maxim Berman Matthew B. Blaschko Amal Rannen Triki Jiaqian Yu 14 2 0 06 Sep 2018