Smart scissor: coupling spatial redundancy reduction and CNN compression for embedded hardware
Scaling down the resolution of input images can greatly reduce the computational overhead of convolutional neural networks (CNNs), which is promising for edge AI. However, as an image usually contains much spatial redundancy, e.g., background pixels, directly shrinking the whole image will lose impo...
Saved in:
Main Authors: | Kong, Hao, Liu, Di, Huai, Shuo, Luo, Xiangzhong, Liu, Weichen, Subramaniam, Ravi, Makaya, Christian, Lin, Qian |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/164833 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Towards efficient convolutional neural network for embedded hardware via multi-dimensional pruning
by: Kong, Hao, et al.
Published: (2023) -
On hardware-aware design and optimization of edge intelligence
by: Huai, Shuo, et al.
Published: (2023) -
EdgeCompress: coupling multi-dimensional model compression and dynamic inference for EdgeAI
by: Kong, Hao, et al.
Published: (2023) -
EvoLP: self-evolving latency predictor for model compression in real-time edge systems
by: Huai, Shuo, et al.
Published: (2023) -
Crossbar-aligned & integer-only neural network compression for efficient in-memory acceleration
by: Huai, Shuo, et al.
Published: (2023)