Unbalanced Encoding in Synchronous Weight Quantization-Compression for Low-Bit Quantized Neural Network.
Yuzhong JiaoSha LiPeng LuoXiao HuoYiu Kei LiPublished in: GCAIoT (2021)
Keyphrases
- neural network
- efficient compression
- uniform quantization
- compression scheme
- image compression
- high compression ratio
- quantization scheme
- adaptive quantization
- tree structured vector quantization
- block coding
- bit rate
- lossy image compression
- artificial neural networks
- weight update
- transform coefficients
- vector quantization
- arithmetic coding
- transform coding
- back propagation
- compression algorithm
- neural network model
- quantization noise
- binary representation
- complexity reduction
- compression ratio
- bit string
- bit wise
- distortion measure
- entropy coding
- compressed data
- low bit rate
- video compression
- gray code
- lossless coding
- quantization error
- bits per pixel
- successive approximation
- transform domain
- data compression
- subband
- lookup table
- shape coding