Learnable Embedding Space for Efficient Neural Architecture Compression

ICLR 2019 • Shengcao Cao • Xiaofang Wang • Kris M. Kitani

We propose a method to incrementally learn an embedding space over the domain of network architectures, to enable the careful selection of architectures for evaluation during compressed architecture search. Given a teacher network, we search for a compressed network architecture by using Bayesian Optimization (BO) with a kernel function defined over our proposed embedding space to select architectures for evaluation... (read more)

PDF Abstract ICLR 2019 PDF ICLR 2019 Abstract

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Random Search	Hyperparameter Search
1x1 Convolution	Convolutions
Grouped Convolution	Convolutions
ReLU	Activation Functions
Batch Normalization	Normalization
Depthwise Convolution	Convolutions
Pointwise Convolution	Convolutions
Residual Connection	Skip Connections
Convolution	Convolutions
Average Pooling	Pooling Operations
Channel Shuffle	Miscellaneous Components
Groupwise Point Convolution	Convolutions
ShuffleNet Block	Image Model Blocks
Global Average Pooling	Pooling Operations
Dense Connections	Feedforward Networks
Max Pooling	Pooling Operations
Softmax	Output Functions
ShuffleNet	Convolutional Neural Networks

METHOD

TYPE

Random Search