A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization
Research in Automatic Speech Recognition (ASR) continues to show that larger models yield better results. But while state-of-the-art networks continue to grow with billions of parameters, the difficulty of deploying these models on device also increases.
Task Generalizable Spatial and Texture Aware Image Downsizing Network
Convolutional neural networks (CNNs) are widely used today in various vision tasks such as classification, detection and segmentation. To make full use of GPU in CNN model processing and to use batch normalization, images of various resolutions are usually resized to the same resolution in the pipeline with mostly used bilinear interpolation.