ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections

2 Aug 2017 Sujith Ravi

Deep neural networks have become ubiquitous for applications related to visual recognition and language understanding tasks. However, it is often prohibitive to use typical neural networks on devices like mobile phones or smart watches since the model sizes are huge and cannot fit in the limited memory available on such devices... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification MNIST ProjectionNet Percentage error 5 # 28
Accuracy 95 # 8

Methods used in the Paper