Zobrazeno 1 - 10
of 192
pro vyhledávání: '"Baluja, Shumeet"'
Simply by rearranging the regions of an image, we can create a new image of any subject matter. The definition of regions is user definable, ranging from regularly and irregularly-shaped blocks, concentric rings, or even individual pixels. Our method
Externí odkaz:
http://arxiv.org/abs/2411.15925
Recent progress in text-to-image (TTI) systems, such as StableDiffusion, Imagen, and DALL-E 2, have made it possible to create realistic images with simple text prompts. It is tempting to use these systems to eliminate the manual task of obtaining na
Externí odkaz:
http://arxiv.org/abs/2311.00056
Autor:
Baluja, Shumeet
Publikováno v:
Communications of the ACM. Oct2011, Vol. 54 Issue 10, p120-119. 2p. 1 Diagram.
Autor:
Baluja, Shumeet
Numerous methods have been proposed to transform color and grayscale images to their single bit-per-pixel binary counterparts. Commonly, the goal is to enhance specific attributes of the original image to make it more amenable for analysis. However,
Externí odkaz:
http://arxiv.org/abs/2105.01768
In this work, we propose to quantize all parts of standard classification networks and replace the activation-weight--multiply step with a simple table-based lookup. This approach results in networks that are free of floating-point operations and fre
Externí odkaz:
http://arxiv.org/abs/1906.04798
A rapidly increasing portion of Internet traffic is dominated by requests from mobile devices with limited- and metered-bandwidth constraints. To satisfy these requests, it has become standard practice for websites to transmit small and extremely com
Externí odkaz:
http://arxiv.org/abs/1812.02831
For successful deployment of deep neural networks on highly--resource-constrained devices (hearing aids, earbuds, wearables), we must simplify the types of operations and the memory/power resources used during inference. Completely avoiding inference
Externí odkaz:
http://arxiv.org/abs/1809.09244
A rapidly increasing portion of internet traffic is dominated by requests from mobile devices with limited and metered bandwidth constraints. To satisfy these requests, it has become standard practice for websites to transmit small and extremely comp
Externí odkaz:
http://arxiv.org/abs/1809.02257
Autor:
Baluja, Shumeet
We present extensive experiments training and testing hidden units in deep networks that emit only a predefined, static, number of discretized values. These units provide benefits in real-world deployment in systems in which memory and/or computation
Externí odkaz:
http://arxiv.org/abs/1801.05156