DUCKQUANT / THE QUANT & AI DIRECTORY
14,444 resources, ranked by in-directory PageRank
Showing 4,717–4,752 of 14,444 resources
Publication: MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?. Published Jan 16, 2020.
Publication: RPR: Random Partition Relaxation for Training; Binary and Ternary Weight Neural Networks. Published Jan 4, 2020.
Publication: Towards Lossless Binary Convolutional Neural Networks Using Piecewise Approximation. Published Aug 8, 2020.
Publication: Understanding Learning Dynamics of Binary Neural Networks via Information Bottleneck. Published Jun 13, 2020.
Publication: Gradient $ell_1$ Regularization for Quantization Robustness. Published Feb 18, 2020.
Publication: Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks. Published Jan 16, 2020.
Publication: Language Models are Few-Shot Learners. Published May 28, 2020.
Publication: What is the State of Neural Network Pruning?. Published Mar 6, 2020.
Publication: A Statistical Framework for Low-bitwidth Training of Deep Neural Networks. Published Oct 27, 2020.
This repository provides code source used in the paper: A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
Publication: Binarized Collaborative Filtering with Distilling Graph Convolutional Networks. Published Jun 5, 2019.
Publication: Towards Fast and Energy-Efficient Binarized Neural Network Inference on FPGA. Published Oct 4, 2018.
Publication: ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. Published Dec 2, 2018.
Publication: Variational Information Distillation for Knowledge Transfer. Published Apr 11, 2019.
Publication: Fighting Quantization Bias With Bias. Published Jun 7, 2019.
Publication: Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation. Published Oct 24, 2019.
Publication: SWALP : Stochastic Weight Averaging in Low-Precision Training. Published Apr 26, 2019.
Publication: Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design. Published Feb 1, 2019.
Publication: Low-bit Quantization of Neural Networks for Efficient Inference. Published Feb 18, 2019.
Codes for AAAI2019 paper: Deep Neural Network Quantization via Layer-Wise Optimization using Limited Training Data
ProxQuant: Quantized Neural Networks via Proximal Operators
Publication: HAQ: Hardware-Aware Automated Quantization With Mixed Precision. Published 2019.
Code for paper "SWALP: Stochastic Weight Averaging forLow-Precision Training".
DNN quantization with outlier channel splitting (ICML'19)
Code for reproducing Flow ++ experiments
Supplementary Code for Unsupervised Neural Quantization for Compressed-Domain Similarity Search
Quantization of Convolutional Neural networks.
Codes for Accepted Paper : "MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization" in NeurIPS 2019
Learning-Recurrent-Binary-Ternary-Weights
Publication: Deep Neural Network Quantization via Layer-Wise Optimization Using Limited Training Data. Published Jul 17, 2019.
Publication: daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices. Published Aug 16, 2019.
Publication: QKD: Quantization-aware Knowledge Distillation. Published Nov 28, 2019.
Publication: Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search. Published Nov 30, 2018.
Publication: The Knowledge Within: Methods for Data-Free Model Compression. Published Dec 3, 2019.
