Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 5 of 5
Full-Text Articles in Physical Sciences and Mathematics
Learning To Align From Scratch, Gary Huang, Marwan Mattar, Honglak Lee, Erik Learned-Miller
Learning To Align From Scratch, Gary Huang, Marwan Mattar, Honglak Lee, Erik Learned-Miller
Erik G Learned-Miller
Unsupervised joint alignment of images has been demonstrated to improve performance on recognition tasks such as face verification. Such alignment reduces undesired variability due to factors such as pose, while only requiring weak supervision in the form of poorly aligned examples. However, prior work on unsupervised alignment of complex, real-world images has required the careful selection of feature representation based on hand-crafted image descriptors, in order to achieve an appropriate, smooth optimization landscape. In this paper, we instead propose a novel combination of unsupervised joint alignment with unsupervised feature learning. Specifically, we incorporate deep learning into the congealing alignment framework. …
Distribution Fields For Tracking, Erik Learned-Miller, Laura Lara
Distribution Fields For Tracking, Erik Learned-Miller, Laura Lara
Erik G Learned-Miller
Visual tracking of general objects often relies on the assumption that gradient descent of the alignment function will reach the global optimum. A common technique to smooth the objective function is to blur the image. However, blurring the image destroys image information, which can cause the target to be lost. To address this problem we introduce a method for building an image descriptor using distribution fields (DFs), a representation that allows smoothing the objective function without destroying information about pixel values. We present experimental evidence on the superiority of the width of the basin of attraction around the global optimum …
Topic Models For Taxonomies, Anton Bakalov, Andrew Mccallum, Hanna Wallach, David Minmo
Topic Models For Taxonomies, Anton Bakalov, Andrew Mccallum, Hanna Wallach, David Minmo
Hanna M. Wallach
Concept taxonomies such as MeSH, the ACM Computing Classification System, and the NY Times Subject Headings are frequently used to help organize data. They typically consist of a set of concept names organized in a hierarchy. However, these names and structure are often not sufficient to fully capture the intended meaning of a taxonomy node, and particularly non-experts may have difficulty navigating and placing data into the taxonomy. This paper introduces two semi-supervised topic models that automatically augment a given taxonomy with many additional keywords by leveraging a corpus of multi-labeled documents. Our experiments show that users find the topics …
A Gpu-Based Approximate Svd Algorithm, Blake Foster, Sridhar Mahadevan, Rui Wang
A Gpu-Based Approximate Svd Algorithm, Blake Foster, Sridhar Mahadevan, Rui Wang
Rui Wang
Approximation of matrices using the Singular Value Decomposition (SVD) plays a central role in many science and engineering applications. However, the computation cost of an exact SVD is prohibitively high for very large matrices. In this paper, we describe a GPU-based approximate SVD algorithm for large matrices. Our method is based on the QUIC-SVD introduced by [6], which exploits a tree-based structure to efficiently discover a subset of rows that spans the matrix space. We describe how to map QUIC-SVD onto the GPU, and improve its speed and stability using a blocked Gram-Schmidt orthogonalization method. Using a simple matrix partitioning …
Topic-Partitioned Multinetwork Embeddings, Peter Krafft, Juston Moore, Bruce Desmarais, Hanna Wallach
Topic-Partitioned Multinetwork Embeddings, Peter Krafft, Juston Moore, Bruce Desmarais, Hanna Wallach
Hanna M. Wallach
We introduce a joint model of network content and context designed for exploratory analysis of email networks via visualization of topic-specific communication patterns. Our model is based on a novel extension of the latent space network model to the mixed-membership framework, and it uses latent Dirichlet allocation to model the text attributes of our data. To perform inference in this model, we use an approximate stochastic expectation-maximization algorithm. We validate the appropriateness of our model using a simulation study and a prediction task, and demonstrate its capabilities by investigating the communication patterns within a new government email dataset, the New …