Showing papers by "Aurelien Lucchi published in 2013"

Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets

Abstract: We propose a working set based approximate sub gradient descent algorithm to minimize the margin-sensitive hinge loss arising from the soft constraints in max-margin learning frameworks, such as the structured SVM. We focus on the setting of general graphical models, such as loopy MRFs and CRFs commonly used in image segmentation, where exact inference is intractable and the most violated constraints can only be approximated, voiding the optimality guarantees of the structured SVM's cutting plane algorithm as well as reducing the robustness of existing sub gradient based methods. We show that the proposed method obtains better approximate sub gradients through the use of working sets, leading to improved convergence properties and increased reliability. Furthermore, our method allows new constraints to be randomly sampled instead of computed using the more expensive approximate inference techniques such as belief propagation and graph cuts, which can be used to reduce learning time at only a small cost of performance. We demonstrate the strength of our method empirically on the segmentation of a new publicly available electron microscopy dataset as well as the popular MSRC data set and show state-of-the-art results.

An Optimal Policy for Target Localization with Application to Electron Microscopy

Abstract: This paper considers the task of finding a target location by making a limited number of sequential observations. Each observation results from evaluating an imperfect classifier of a chosen cost and accuracy on an interval of chosen length and position. Within a Bayesian framework, we study the problem of minimizing an objective that combines the entropy of the posterior distribution with the cost of the questions asked. In this problem, we show that the one-step lookahead policy is Bayes-optimal for any arbitrary time horizon. Moreover, this one-step lookahead policy is easy to compute and implement. We then use this policy in the context of localizing mitochondria in electron microscope images, and experimentally show that significant speed ups in acquisition can be gained, while maintaining near equal image quality at target locations, when compared to current policies.

Flash Scanning Electron Microscopy

Abstract: Scanning Electron Microscopy (SEM) is an invaluable tool for biologists and neuroscientists to study brain structure at the intracellular level.While able to image tissue samples with up to 5nm isotropic resolution, image acquisition is prohibitively slow and limits the size of processed samples. In this work, we propose a novel approach to speeding up imaging when looking for specific structures. Unlike earlier methods, we explicitly balance the conflicting requirements of spending enough time scanning potential regions of interest to ensure that all targets are found while not wasting time on unpromising regions. This is achieved by using a Markov Random Field to model target locations and optimizing scanning locations by using a Branch-and-Bound strategy. We show that our approach significantly outperforms state-of-the-art methods to locate mitochondria in brain tissue.