二值化
文章平均质量分 93
京哥搞异构AI
一只龟速前进的小强
展开
-
[京哥读论文]之BinaryConnect:Training Deep Neural Networks with binary weights during propagations
论文题目:BinaryConnect: Training Deep Neural Networks with binary weights during propagations_NIPS2015引用量:927code:https://github.com/MatthieuCourbariaux/BinaryConnect这是我看的第一篇提出在DNN的前向和反向训练中用1bit的二值权重替代...原创 2019-08-14 14:43:56 · 714 阅读 · 1 评论 -
[京哥读论文]之BNN:Training deep neural networks with weights and activations constrained to+ 1 or-1
论文题目: Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1引用量:908code: https://github.com/itayhubara/BinaryNetBNN作者与BinaryConnect是同一个人,还有一个论文...原创 2019-08-14 14:46:16 · 1265 阅读 · 0 评论 -
[京哥读论文]之XNOR再读感想
论文题目:XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks_ECCV2016引用量:1346code:https://github.com/allenai/XNOR-Net,https://github.com/jiecaoyu/XNOR-Net-PyTorch这篇论文主要提出了两个网络...原创 2019-08-15 23:05:59 · 441 阅读 · 0 评论 -
[京哥读论文]之Bi-Real Net:Enhancing the Performance of 1-bit CNNs With Improved Representational Capabilit
论文题目:Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm_ECCV2018引用量:27code:caffe版:https://github.com/liuzechun/Bi-Real-net...原创 2019-08-15 23:07:33 · 666 阅读 · 0 评论 -
[京哥读论文]之ABC-Net:Towards Accurate Binary Convolutional Neural Network
论文题目:Towards Accurate Binary Convolutional Neural Network_NIPS2017引用量:98code:https://github.com/layog/Accurate-Binary-Convolution-Networkhttps://github.com/cow8/ABC-Net-pytorch由于之前二值化工作在ImageNet数据...原创 2019-08-15 23:08:48 · 724 阅读 · 0 评论 -
[京哥读论文]之From Hashing to CNNs: Training Binary Weight Networks via Hashing
Abstract本文在二值化权重(BWN)方面做出了创新,发表在AAAI2018上,作者是自动化所程建团队。本文的主要贡献是提出了一个新的训练BWN的方法,揭示了哈希与BW(Binary Weights)之间的关联,表明训练BWN的方法在本质上可以当做一个哈希问题。基于这个方法,本文还提出了一种交替更新的方法来有效的学习hash codes而不是直接学习Weights。在小数据和大数据集上表现...原创 2018-06-05 09:10:35 · 1128 阅读 · 0 评论 -
[京哥读论文]之XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Abstract本文是一篇经典的二值化weight和activations的文章,发表在ECCV2016.本文提出了两种有效二值化的框架:XNOR−NetXNOR−NetXNOR-Net以及BWNBWNBWN(Binary-Weight-Networks).在存储方面可以节省32倍的memory。在XNOR−NetXNOR−NetXNOR-Net上weights以及卷积层的input都是二值化...原创 2018-06-26 22:09:08 · 642 阅读 · 0 评论 -
[京哥读论文]之Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM
Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMMAbstract在DeepLearning日益发展的同时,模型压缩的关注度也越来越大。继BWN和TWN之后, 这篇论文在超低比特量化领域的一篇新思想文章,发表在AAAI2018上,作者是阿里的。 该文的主要思想是将超低bit quantizatio...原创 2018-06-01 15:51:17 · 1469 阅读 · 0 评论