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...
Saved in:
Main Authors | , |
---|---|
Format | Journal Article |
Language | English |
Published |
23.07.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Be the first to leave a comment!