SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another dimension reduction method, adaptive sampling weights and proces...

Full description

Saved in:
Bibliographic Details
Main Authors Kwan, Ho Man, Song, Shenghui
Format Journal Article
LanguageEnglish
Published 23.07.2022
Subjects
Online AccessGet full text

Cover

Loading…