Efficient Learning for Discriminative Segmentation with Supermodular Losses - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Efficient Learning for Discriminative Segmentation with Supermodular Losses


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 (SVM). These loss functions do not necessarily have the same structure as the segmentation inference algorithm, and in general, we may have to resort to generic submodular minimization algorithms for loss augmented inference. Although these come with polynomial time guarantees, they are not practical to apply to image scale data. Many supermodular losses come with strong optimization guarantees, but are not readily incorporated in a loss augmented graph cuts procedure. This motivates our strategy of employing the alternating direction method of multipliers (ADMM) decomposition for loss augmented inference. In doing so, we create a new API for the structured SVM that separates the maximum a posteriori (MAP) inference of the model from the loss augmentation during training. In this way, we gain computational efficiency, making new choices of loss functions practical for the first time, while simultaneously making the inference algorithm employed during training closer to the test time procedure. We show improvement both in accuracy and computational performance on the Microsoft Research Grabcut database and a brain structure segmentation task, empirically validating the use of a supermodular loss during training, and the improved computational properties of the proposed ADMM approach over the Fujishige-Wolfe minimum norm point algorithm.
Fichier principal
Vignette du fichier
final35.pdf (6.27 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01349000 , version 1 (26-07-2016)


  • HAL Id : hal-01349000 , version 1


Jiaqian Yu, Matthew Blaschko. Efficient Learning for Discriminative Segmentation with Supermodular Losses. British Machine Vision Conference, Sep 2016, York, United Kingdom. ⟨hal-01349000⟩
141 View
426 Download


Gmail Facebook X LinkedIn More