TAC framework separates optimization of convolutional and fully connected layers in 1-bit DNNs to improve accuracy while maintaining efficiency.
Learning efficient convolutional networks through network slimming[C]//Computer Vision (ICCV), 2017 IEEE International Conference on
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Targeted Acceleration and Compression Framework for Low bit Neural Networks
TAC framework separates optimization of convolutional and fully connected layers in 1-bit DNNs to improve accuracy while maintaining efficiency.