92 citations · 276 across the 12 of their papers we have counts for
15 papers
Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models
Xiaofang Wang, Dan Kondratyuk, Eric Christiansen +3
Committee-based models (ensembles or cascades) construct models by combining existing pre-trained ones. While ensembles and cascades are well-known techniques that were proposed be…
Neighbourhood Distillation: On the benefits of non end-to-end distillation
Laëtitia Shao, Max Moroz, Elad Eban +1
End-to-end training with back propagation is the standard method for training deep neural networks. However, as networks become deeper and bigger, end-to-end training becomes more…
Fine-Grained Stochastic Architecture Search
Shraman Ray Chaudhuri, Elad Eban, Hanhan Li +2
State-of-the-art deep networks are often too large to deploy on mobile devices and embedded systems. Mobile neural architecture search (NAS) methods automate the design of small mo…
Sky Optimization: Semantically aware image processing of skies in low-light photography
Orly Liba, Longqi Cai, Yun-Ta Tsai +5
The sky is a major component of the appearance of a photograph, and its color and tone can strongly influence the mood of a picture. In nighttime photography, the sky can also suff…
Computationally Efficient Neural Image Compression
Nick Johnston, Elad Eban, Ariel Gordon +1
Image compression using neural networks have reached or exceeded non-neural methods (such as JPEG, WebP, BPG). While these networks are state of the art in ratedistortion performan…
Structured Multi-Hashing for Model Compression
Elad Eban, Yair Movshovitz-Attias, Hao Wu +4
Despite the success of deep neural networks (DNNs), state-of-the-art models are too large to deploy on low-resource devices or common server configurations in which multiple models…