Replacement Learning replaces selected blocks in CNNs and ViTs with learnable parameter-fusion surrogates derived from adjacent layers to reduce full-depth backpropagation redundancy.
Learning internal representations by error propagation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Replacement Learning: Training Neural Networks with Fewer Parameters
Replacement Learning replaces selected blocks in CNNs and ViTs with learnable parameter-fusion surrogates derived from adjacent layers to reduce full-depth backpropagation redundancy.