Karol Gregor
New York University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Karol Gregor.
european conference on computer vision | 2012
Arthur Szlam; Karol Gregor; Yann LeCun
We describe a method for fast approximation of sparse coding. A given input vector is passed through a binary tree. Each leaf of the tree contains a subset of dictionary elements. The coefficients corresponding to these dictionary elements are allowed to be nonzero and their values are calculated quickly by multiplication with a precomputed pseudoinverse. The tree parameters, the dictionary, and the subsets of the dictionary corresponding to each leaf are learned. In the process of describing this algorithm, we discuss the more general problem of learning the groups in group structured sparse modeling. We show that our method creates good sparse representations by using it in the object recognition framework of [1,2]. Implementing our own fast version of the SIFT descriptor the whole system runs at 20 frames per second on 321 ×481 sized images on a laptop with a quad-core cpu, while sacrificing very little accuracy on the Caltech 101, Caltech 256, and 15 scenes benchmarks.
Science | 2018
S. M. Ali Eslami; Danilo Jimenez Rezende; Frederic Besse; Fabio Viola; Ari S. Morcos; Marta Garnelo; Avraham Ruderman; Andrei A. Rusu; Ivo Danihelka; Karol Gregor; David P. Reichert; Lars Buesing; Theophane Weber; Oriol Vinyals; Dan Rosenbaum; Neil C. Rabinowitz; Helen King; Chloe Hillier; Matt Botvinick; Daan Wierstra; Koray Kavukcuoglu; Demis Hassabis
A scene-internalizing computer program To train a computer to “recognize” elements of a scene supplied by its visual sensors, computer scientists typically use millions of images painstakingly labeled by humans. Eslami et al. developed an artificial vision system, dubbed the Generative Query Network (GQN), that has no need for such labeled data. Instead, the GQN first uses images taken from different viewpoints and creates an abstract description of the scene, learning its essentials. Next, on the basis of this representation, the network predicts what the scene would look like from a new, arbitrary viewpoint. Science, this issue p. 1204 A computer vision system predicts how a 3D scene looks from any viewpoint after just a few 2D views from other viewpoints. Scene representation—the process of converting visual sensory data into concise descriptions—is a requirement for intelligent behavior. Recent work has shown that neural networks excel at this task when provided with large, labeled datasets. However, removing the reliance on human labeling remains an important open problem. To this end, we introduce the Generative Query Network (GQN), a framework within which machines learn to represent scenes using only their own sensors. The GQN takes as input images of a scene taken from different viewpoints, constructs an internal representation, and uses this representation to predict the appearance of that scene from previously unobserved viewpoints. The GQN demonstrates representation learning without human labels or domain knowledge, paving the way toward machines that autonomously learn to understand the world around them.
neural information processing systems | 2010
Koray Kavukcuoglu; Pierre Sermanet; Y-Lan Boureau; Karol Gregor; Michael Mathieu; Yann Le Cun
international conference on machine learning | 2010
Karol Gregor; Yann LeCun
neural information processing systems | 2011
Arthur Szlam; Karol Gregor; Yann Le Cun
neural information processing systems | 2016
Karol Gregor; Frederic Besse; Danilo Jimenez Rezende; Ivo Danihelka; Daan Wierstra
arXiv: Neural and Evolutionary Computing | 2010
Karol Gregor; Yann LeCun
arXiv: Learning | 2016
Karol Gregor; Danilo Jimenez Rezende; Daan Wierstra
arXiv: Computer Vision and Pattern Recognition | 2011
Karol Gregor; Yann LeCun
arXiv: Computer Vision and Pattern Recognition | 2011
Karol Gregor; Yann LeCun
Collaboration
Dive into the Karol Gregor's collaboration.
Dalle Molle Institute for Artificial Intelligence Research
View shared research outputs