journalarticle
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
International Conference on Machine Learning2018-10-16 423 citations33 references
Looking for the full paper…
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
No abstract is available from our sources. Use “Read paper” to view it.
TL;DRThe Shallow-Deep Network (SDN) is proposed, a generic modification to off-the-shelf DNNs that introduces internal classifiers that can mitigate the wasteful effect of overthinking with confidence-based early exits and reduce the average inference cost by more than 50% and preserve the accuracy. (Semantic Scholar)