A single convolutional neural mixture model, trained once, yields a wide range of accuracy-compute operating points through learned probabilistic pruning of depth paths and early-exit classifiers.
Maskconnect: Con- nectivity learning by gradient descent
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptative Inference Cost With Convolutional Neural Mixture Models
A single convolutional neural mixture model, trained once, yields a wide range of accuracy-compute operating points through learned probabilistic pruning of depth paths and early-exit classifiers.