Optimizing the Bit Allocation for Compression of Weights and Activations of Deep Neural Networks.
Wang ZheJie LinVijay ChandrasekharBernd GirodPublished in: ICIP (2019)
Keyphrases
- bit allocation
- neural network
- image compression
- rate distortion
- video compression
- bit rate
- compression efficiency
- vector quantizer
- rate control
- video coding
- transform coding
- low bit rate
- video quality
- vector quantization
- video coder
- compression ratio
- image coding
- reconstructed image
- compression scheme
- motion compensation
- wavelet transform
- compression algorithm
- macroblock
- subband
- bitstream
- multi layer
- visual quality
- inter frame
- frame rate
- markov decision processes
- video conferencing
- model checking
- motion vectors
- image quality
- video sequences
- data structure
- high quality