BCAE-VS compresses sparse detector data by selecting key signal voxels with a sparse-convolution encoder, achieving lower error and higher compression than prior BCAE autoencoders at much smaller model size.
URL https://indico.bnl.gov/event/5905/
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.ins-det 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Variable Rate Neural Compression for Sparse Detector Data
BCAE-VS compresses sparse detector data by selecting key signal voxels with a sparse-convolution encoder, achieving lower error and higher compression than prior BCAE autoencoders at much smaller model size.