Showing papers by "Jeffrey Dean published in 2014"
•
01 Jan 2014TL;DR: A simple method for constructing an image embedding system from any existing image classifier and a semantic word embedding model, which contains the $
$ class labels in its vocabulary is proposed, which outperforms state of the art methods on the ImageNet zero-shot learning task.
Abstract: Several recent publications have proposed methods for mapping images into continuous semantic embedding spaces. In some cases the embedding space is trained jointly with the image transformation. In other cases the semantic embedding space is established by an independent natural language processing task, and then the image transformation into that space is learned in a second stage. Proponents of these image embedding systems have stressed their advantages over the traditional
way{} classification framing of image understanding, particularly in terms of the promise for zero-shot learning -- the ability to correctly annotate images of previously unseen object categories. In this paper, we propose a simple method for constructing an image embedding system from any existing
way{} image classifier and a semantic word embedding model, which contains the $
$ class labels in its vocabulary. Our method maps images into the semantic embedding space via convex combination of the class label embedding vectors, and requires no additional training. We show that this simple and direct method confers many of the advantages associated with more complex image embedding schemes, and indeed outperforms state of the art methods on the ImageNet zero-shot learning task.
853 citations
••
Yale University1, Microsoft2, École Polytechnique Fédérale de Lausanne3, University of Washington4, University of California, Irvine5, Google6, University of Wisconsin-Madison7, University of California, Berkeley8, IBM9, National and Kapodistrian University of Athens10, ETH Zurich11, Massachusetts Institute of Technology12, Tel Aviv University13, Technical University of Berlin14, National University of Singapore15, Stanford University16
TL;DR: It is observed that Big Data has now become a defining challenge of the authors' time, and that the database research community is uniquely positioned to address it, with enormous opportunities to make transformative impact.
Abstract: Every few years a group of database researchers meets to discuss the state of database research, its impact on practice, and important new directions. This report summarizes the discussion and conclusions of the eighth such meeting, held October 14- 15, 2013 in Irvine, California. It observes that Big Data has now become a defining challenge of our time, and that the database research community is uniquely positioned to address it, with enormous opportunities to make transformative impact. To do so, the report recommends significantly more attention to five research areas: scalable big/fast data infrastructures; coping with diversity in the data management landscape; end-to-end processing and understanding of data; cloud services; and managing the diverse roles of people in the data life cycle.
110 citations
•
13 Mar 2014TL;DR: In this article, a set of relevance scores for each concept term in a pre-determined set of concept terms is calculated, where each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource.
Abstract: 16113-4691WO1 Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, 5 wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values to generate an alternative representation of the features of the resource, wherein processing the numeric values comprises applying one or more non-linear transformations to the numeric values; and processing the alternative 10 representation of the input to generate a respective relevance score for each concept term in a pre-determined set of concept terms, wherein each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource.
25 citations
•
27 Oct 2014TL;DR: In this article, a method of processing a request, performed by a respective server, is provided in which a request is received from a client, and a determination is made as to whether at least a first predefined number of other servers have a task-processing status for the request indicating that the other servers had undertaken performance of a task processing operation for the requested request.
Abstract: A method of processing a request, performed by a respective server, is provided in which a request is received from a client. After receiving the request, a determination is made as to whether at least a first predefined number of other servers have a task-processing status for the request indicating that the other servers have undertaken performance of a task-processing operation for the request. When less than the first number of other servers in the set of other servers have the task-processing status for the request, a processing-status message is sent to one or more of the servers in the set of other servers indicating that the respective server is performing the task-processing operation. Upon completion of the task-processing, a result of the processing is sent to the client contingent upon a status of the other servers in the set of other servers.
17 citations