TempDiff: Temporal Difference-Based Feature Map-Level Sparsity Induction in CNNs with <4% Memory Overhead
IEEE
Saved in:
Main Authors: | WATHUTHANTHRIGE UDARI CHARITHA DE ALWIS, ALIOTO,MASSIMO BRUNO |
---|---|
Other Authors: | ELECTRICAL AND COMPUTER ENGINEERING |
Format: | Article |
Published: |
IEEE
2021
|
Subjects: | |
Online Access: | https://scholarbank.nus.edu.sg/handle/10635/189401 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | National University of Singapore |
Similar Items
-
TempDiff: Feature Map-Level CNN Sparsity Enhancement at Near-Zero Memory Overhead via Temporal Difference
by: WATHUTHANTHRIGE UDARI CHARITHA DE ALWIS, et al.
Published: (2023) -
TempDiff: Temporal Difference-Based Feature Map-Level Sparsity Induction in CNNs with <4% Memory Overhead
by: De Alwis, Udari, et al.
Published: (2021) -
Architecture for 3D Convolutional Neural Networks Based on Temporal Similarity Removal
by: WATHUTHANTHRIGE UDARI CHARITHA DE ALWIS, et al.
Published: (2023) -
Temporal Redundancy-Based Computation Reduction for 3D Convolutional Neural Networks
by: Udari De Alwis, et al.
Published: (2022) -
MACHINE LEARNING ACCELERATION FOR EDGE COMPUTING IN DISTRIBUTED SENSOR NETWORKS
by: DE ALWIS WATHUTHANTHRIGE UDARI CHARITHA
Published: (2023)