A U-Net variant using channel-wise 1D convolutions and pixel-shuffle operations substantially reduces model size, but the claim of accuracy preservation is contradicted by the paper's own results on general datasets.
Imagenet: A large-scale hierarchical image database
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
OneNet: A Channel-Wise 1D Convolutional U-Net
A U-Net variant using channel-wise 1D convolutions and pixel-shuffle operations substantially reduces model size, but the claim of accuracy preservation is contradicted by the paper's own results on general datasets.