SaneDL detects invalid inputs by using autoencoder reconstruction losses of intermediate activations as assertions, reporting high detection rates on two image dataset pairs.
A domain strategy for computer program testing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Data Sanity Check for Deep Learning Systems via Learnt Assertions
SaneDL detects invalid inputs by using autoencoder reconstruction losses of intermediate activations as assertions, reporting high detection rates on two image dataset pairs.