Quantization has emerged as an essential technique for deploying deep ne...
Quantization of transformer language models faces significant challenges...
The previous deep video compression approaches only use the single scale...
Knowledge distillation is an effective method to improve the performance...
Unsupervised learning has been popular in various computer vision tasks,...
FPGA accelerators designed for graph processing are gaining popularity.
...
In this paper, we propose a new deep image compression framework called
...
In this work, we propose a new layer-by-layer channel pruning method cal...