A look-aside adapter with 1D time and frequency convolutions lets a frozen vision transformer match or beat audio-pretrained models on audio classification benchmarks.
However, it is challenging due to the need of substantial audio data and a well-designed learning objective for large-scale audio pretraining
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1roles
dataset 1polarities
background 1representative citing papers
citing papers explorer
-
When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining
A look-aside adapter with 1D time and frequency convolutions lets a frozen vision transformer match or beat audio-pretrained models on audio classification benchmarks.