A companion 'ghost' network built from inter-layer activation correlations is pruned and its mask is mapped back to the original network, with small accuracy gains on some synthetic distribution shifts but with a flawed theoretical explanation.
How does loss function affect generalization per- formance of deep learning? application to human age esti- mation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Ghost-Connect Net: A Generalization-Enhanced Guidance For Sparse Deep Networks Under Distribution Shifts
A companion 'ghost' network built from inter-layer activation correlations is pruned and its mask is mapped back to the original network, with small accuracy gains on some synthetic distribution shifts but with a flawed theoretical explanation.