223 citations · 232 across the 4 of their papers we have counts for
9 papers
Texture for Colors: Natural Representations of Colors Using Variable Bit-Depth Textures
Shumeet Baluja
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…
Table-Based Neural Units: Fully Quantizing Networks for Multiply-Free Inference
Michele Covell, David Marwood, Shumeet Baluja +1
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…
Neural Image Decompression: Learning to Render Better Image Previews
Shumeet Baluja, Dave Marwood, Nick Johnston +1
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 bec…
No Multiplication? No Floating Point? No Problem! Training Networks for Efficient Inference
Shumeet Baluja, David Marwood, Michele Covell +1
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 memor…
Representing Images in 200 Bytes: Compression via Triangulation
David Marwood, Pascal Massimino, Michele Covell +1
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 beco…
Empirical Explorations in Training Networks with Discrete Activations
Shumeet Baluja
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…