Inter-region affinity distillation for road marking segmentation
We study the problem of distilling knowledge from a large deep teacher network to a much smaller student net- work for the task of road marking segmentation. In this work, we explore a novel knowledge distillation (KD) ap- proach that can transfer ‘knowledge’ on scene structure more effectively...
Saved in:
Main Authors: | Hou, Yuenan, Ma, Zheng, Liu, Chunxiao, Hui, Tak-Wai, Loy, Chen Change |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/161798 https://openaccess.thecvf.com/menu |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Solar Power Integration in Water (H2O) Distillation (SPIN-HD)
by: Carlos, Charlize F., et al.
Published: (2021) -
Trajectory based optimal segment computation in road network databases
by: Li, X., et al.
Published: (2014) -
Computation-efficient knowledge distillation via uncertainty-aware mixup
by: Xu, Guodong, et al.
Published: (2023) -
Agentive marking in Yongning Na (Mosuo)
by: Lidz, Liberty A.
Published: (2024) -
Effect of humic-acid fouling on membrane distillation
by: Tan, Yong Zen, et al.
Published: (2017)