DUCKQUANT / THE QUANT & AI DIRECTORY
14,444 resources, ranked by in-directory PageRank
Showing 4,753–4,788 of 14,444 resources
Publication: Regularizing Activation Distribution for Training Binarized Deep Networks. Published Apr 4, 2019.
Publication: Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks. Published Sep 28, 2019.
Publication: Mixed Precision Training With 8-bit Floating Point. Published May 29, 2019.
Publication: Accurate and Compact Convolutional Neural Networks with Trained Binarization. Published Sep 25, 2019.
Publication: Knowledge distillation for optimization of quantized deep neural networks. Published Sep 4, 2019.
Publication: Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers. Published Sep 5, 2019.
Publication: MoBiNet: A Mobile Binary Network for Image Classification. Published Jul 29, 2019.
Publication: Back to Simplicity: How to Train Accurate BNNs from Scratch?. Published Jun 19, 2019.
Publication: Matrix and tensor decompositions for training binary neural networks. Published Apr 16, 2019.
Publication: Binarized Neural Architecture Search. Published Nov 25, 2019.
Publication: Improved training of binary networks for human pose estimation and image recognition. Published Apr 11, 2019.
Publication: TentacleNet: A Pseudo-Ensemble Template for Accurate Binary Convolutional Neural Networks. Published Dec 20, 2019.
Publication: RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs. Published Aug 21, 2019.
Publication: Similarity Preserving Deep Asymmetric Quantization for Image Retrieval. Published Jul 17, 2019.
Publication: Multi-Precision Quantized Neural Networks via Encoding Decomposition of -1 and +1. Published May 31, 2019.
Publication: Efficient Quantization for Neural Networks with Binary Weights and Low Bitwidth Activations. Published Jul 17, 2019.
Publication: Mixed Precision Training of Convolutional Neural Networks using Integer Operations. Published Feb 3, 2018.
Publication: AMC: AutoML for Model Compression and Acceleration on Mobile Devices. Published Feb 10, 2018.
Publication: Moonshine: Distilling with Cheap Convolutions. Published Nov 7, 2017.
Publication: A Quantization-Friendly Separable Convolution for MobileNets. Published Mar 22, 2018.
Publication: Inference of Quantized Neural Networks on Heterogeneous All-Programmable Devices. Published Jun 21, 2018.
Publication: FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks. Published Sep 12, 2018.
Abstract page for arXiv paper 1902.01917: Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization
Publication: Learned Step Size Quantization. Published Feb 21, 2019.
Code example for the ICLR 2018 oral paper
Implements quantized distillation. Code for our paper "Model compression via distillation and quantization"
Code for paper "Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking"
This repository represents training examples for the CVPR 2018 paper "SYQ:Learning Symmetric Quantization For Efficient Deep Neural Networks"
Explore this resource at its source website for documentation and current information.
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm. In ECCV 2018 and IJCV
Public repository by eladhoffer. Primary language: Python.
Publication: LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks. Published 2018.
Publication: Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization. Published Aug 3, 2017.
Publication: TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning. Published May 22, 2017.
