Reconstruction from group-invariant networks collapses toward the orbit-average input, and two modified methods (SAME-GD, deep image prior) reduce this collapse in preliminary MNIST experiments.
Deconstructing data reconstruction: Multiclass, weight decay and general losses
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Reconstruction of Training Data from Group Invariant Networks
Reconstruction from group-invariant networks collapses toward the orbit-average input, and two modified methods (SAME-GD, deep image prior) reduce this collapse in preliminary MNIST experiments.