The tradeoff between performance and inference speed is critical for practical applications.
Architecture reparameterization obtains better tradeoffs and it is becoming an increasingly …

Current model quantization methods have shown their promising capability in reducing
storage space and computation complexity. However, due to the diversity of quantization …

This paper addresses the face recognition task for offline mobile applications. Using AutoML
techniques, a novel technological framework is proposed to develop a fast neural network …

Quantization is an effective way to compress neural networks. By reducing the bit width of
the parameters, the processing efficiency of neural network models at edge devices can be …

Deep learning technologies have demonstrated remarkable effectiveness in a wide range of
tasks, and deep learning holds the potential to advance a multitude of applications …

Deep neural network quantization with adaptive bitwidths has gained increasing attention
due to the ease of model deployment on various platforms with different resource budgets. In …

Deep Neural Network (DNN) inference based on quantized narrow-precision integer data
represents a promising research direction toward efficient deep learning computations on …

Blending multiple convolutional kernels is proved advantageous in neural architecture
design. However, current two-stage neural architecture search methods are mainly limited to …

Deep convolutional networks are increasingly applied in mobile AI scenarios. To achieve
efficient deployment researchers combine neural architecture search (NAS) and …

Abstract The combination of Neural Architecture Search (NAS) and quantization has proven
successful in automatically designing low-FLOPs INT8 quantized neural networks (QNN) …