Deep networks run with low precision operations at inference time offer power and space
advantages over high precision alternatives, but need to overcome the challenge of …

As the popularity of mobile photography is growing constantly, lots of efforts are being
invested now into building complex hand-crafted camera ISP solutions. In this work, we …

Neural network quantization enables the deployment of large models on resource-
constrained devices. Current post-training quantization methods fall short in terms of …

We propose a method of training quantization thresholds (TQT) for uniform symmetric
quantizers using standard backpropagation and gradient descent. Contrary to prior work, we …

The exponentially large discrete search space in mixed-precision quantization (MPQ) makes
it hard to determine the optimal bit-width for each layer. Previous works usually resort to …

Abstract Model quantization has emerged as a mandatory technique for efficient inference
with advanced Deep Neural Networks (DNN). It converts the model parameters in full …

Neural network quantization methods often involve simulating the quantization process
during training, making the trained model highly dependent on the target bit-width and …

Recent work in network quantization produced state-of-the-art results using mixed precision
quantization. An imperative requirement for many efficient edge device hardware …

Abstract Model quantization is an important mechanism for energy-efficient deployment of
deep neural networks on resource-constrained devices by reducing the bit precision of …

Analog electronic and optical computing exhibit tremendous advantages over digital
computing for accelerating deep learning when operations are executed at low precision …