From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers.

Jiu Feng Mehmet Hamza Erol Joon Son Chung Arda Senocak

Published in: ICASSP (2024)

Keyphrases

coarse to fine
multiresolution
multiscale
object detection
image registration
hierarchical segmentation
hierarchical representation
active shape model
dynamic programming
optical flow estimation