B
Benoit Seguin
Researcher at École Polytechnique Fédérale de Lausanne
Publications - 10
Citations - 324
Benoit Seguin is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Deep learning & Task (project management). The author has an hindex of 6, co-authored 10 publications receiving 208 citations.
Papers
More filters
Proceedings ArticleDOI
dhSegment: A Generic Deep-Learning Approach for Document Segmentation
TL;DR: This paper proposes an open-source implementation of a CNN-based pixel-wise predictor coupled with task dependent post-processing blocks and shows that a single CNN-architecture can be used across tasks with competitive results.
Book ChapterDOI
Visual Link Retrieval in a Database of Paintings
TL;DR: It is shown that pre-trained convolutional neural network can perform better for this task than other machine vision methods aimed at photograph analysis and retrieval performance can be significantly improved by fine-tuning a network specifically for thistask.
Proceedings ArticleDOI
dhSegment: A generic deep-learning approach for document segmentation.
TL;DR: In this paper, an open-source implementation of a CNN-based pixel-wise predictor coupled with task dependent post-processing blocks is proposed. But the authors argue that the diversity of historical document processing tasks prohibits to solve them one at a time and shows a need for designing generic approaches in order to handle the variability of historical series.
Proceedings ArticleDOI
Deep Learning for Logic Optimization Algorithms
Winston Haaswijk,Edo Collins,Benoit Seguin,Mathias Soeken,Frédéric Kaplan,Sabine Süsstrunk,Giovanni De Micheli +6 more
TL;DR: In this paper, the authors cast logic optimization as a deterministic Markov decision process (MDP) and used deep reinforcement learning to train a system to navigate this process automatically and without human intervention.
Journal ArticleDOI
The Replica Project: Building a visual search engine for art historians
TL;DR: From the time of prehistoric etchings on the walls of the Lascaux cave to the present day, people have always been creating art.