SplitEE: Early Exit in Deep Neural Networks with Split Computing
Open paper
Benchmark
Model
Rank
Results
natural-language-inference-on-scitail
SplitEE-S
#6
Accuracy: 78.9
paraphrase-identification-on-quora-question-pairs
SplitEE-S
#27
Accuarcy: 71.1
natural-language-inference-on-snli
SplitEE-S
#73
Accuracy: 79.0
Rank counts only results with a code link.