O
Ozan Sener
Researcher at Intel
Publications - 50
Citations - 4146
Ozan Sener is an academic researcher from Intel. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 18, co-authored 45 publications receiving 3038 citations. Previous affiliations of Ozan Sener include King Abdullah University of Science and Technology & Middle East Technical University.
Papers
More filters
Proceedings ArticleDOI
3D Semantic Parsing of Large-Scale Indoor Spaces
Iro Armeni,Ozan Sener,Amir Roshan Zamir,Helen Jiang,Ioannis Brilakis,Martin Fischer,Silvio Savarese +6 more
TL;DR: This paper argues that identification of structural elements in indoor spaces is essentially a detection problem, rather than segmentation which is commonly used, and proposes a method for semantic parsing the 3D point cloud of an entire building using a hierarchical approach.
Proceedings Article
Active Learning for Convolutional Neural Networks: A Core-Set Approach
Ozan Sener,Silvio Savarese +1 more
TL;DR: This work defines the problem of active learning as core-set selection as choosing set of points such that a model learned over the selected subset is competitive for the remaining data points, and presents a theoretical result characterizing the performance of any selected subset using the geometry of the datapoints.
Posted Content
Multi-Task Learning as Multi-Objective Optimization
Ozan Sener,Vladlen Koltun +1 more
TL;DR: This paper cast multi-task learning as a multi-objective optimization problem, with the overall objective of finding a Pareto optimal solution, and propose an upper bound for the multiobjective loss and show that it can be optimized efficiently.
Proceedings Article
Learning Transferrable Representations for Unsupervised Domain Adaptation
TL;DR: A unified deep learning framework where the representation, cross domain transformation, and target label inference are all jointly optimized in an end-to-end fashion for unsupervised domain adaptation is proposed.
Proceedings Article
Multi-Task Learning as Multi-Objective Optimization
Ozan Sener,Vladlen Koltun +1 more
TL;DR: This paper proposes an upper bound for the multi-objective loss and shows that it can be optimized efficiently, and proves that optimizing this upper bound yields a Pareto optimal solution under realistic assumptions.