DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks

no code implementations • ECCV 2020 • Hassan Dbouk, Hetul Sanghvi, Mahesh Mehendale, Naresh Shanbhag

While various complexity reduction techniques, such as lightweight network architecture design and parameter quantization, have been successful in reducing the cost of implementing these networks, these methods have often been considered orthogonal.

Quantization