Efficient learning for discriminative segmentation with supermodular losses
| Autor: | Jiaqian Yu, Matthew B. Blaschko |
|---|---|
| Přispěvatelé: | Organ Modeling through Extraction, Representation and Understanding of Medical Image Content (GALEN), Ecole Centrale Paris-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Centre de vision numérique (CVN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec, Departement Elektrotechniek - ESAT [leuven], Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Ecole Centrale Paris |
| Jazyk: | angličtina |
| Rok vydání: | 2016 |
| Předmět: |
Mathematical optimization
PSI_MBL Structured support vector machine Inference [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Image segmentation 010501 environmental sciences 01 natural sciences 030218 nuclear medicine & medical imaging Submodular set function Support vector machine 03 medical and health sciences GrabCut 0302 clinical medicine [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] Maximum a posteriori estimation Time complexity 0105 earth and related environmental sciences Mathematics |
| Zdroj: | British Machine Vision Conference British Machine Vision Conference, Sep 2016, York, United Kingdom BMVC |
| Popis: | International audience; 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|