{"id":22088,"date":"2020-01-16T23:45:37","date_gmt":"2020-01-16T14:45:37","guid":{"rendered":"https:\/\/blog.yokokanno.com\/?page_id=22088"},"modified":"2022-09-27T10:39:57","modified_gmt":"2022-09-27T01:39:57","slug":"go-deepest","status":"publish","type":"page","link":"https:\/\/blog.yokokanno.com\/?page_id=22088","title":{"rendered":"GO DEEPEST"},"content":{"rendered":"

\u3010Tips\u3011
\n\u30fbdlbook_notation<\/a>
\n\u30fbFormatting Instructions for ICLR2020 Conference Submissions<\/a>
\n\u30fb\u30c8\u30c3\u30d7\u30ab\u30f3\u30d5\u30a1\u30ec\u30f3\u30b9\u3078\u306e\u8ad6\u6587\u63a1\u629e\u306b\u5411\u3051\u3066\uff08AI\u7814\u7a76\u5206\u91ce\u7248\uff09<\/a>
\n\u30fbAI\u7cfb\u30c8\u30c3\u30d7\u30ab\u30f3\u30d5\u30a1\u30ec\u30f3\u30b9\u3078\u306e\u8ad6\u6587\u63a1\u629e\u306b\u5411\u3051\u305f\u8a66\u9a13\u5bfe\u7b56<\/a>
\n\u30fb\u30c8\u30c3\u30d7\u30ab\u30f3\u30d5\u30a1\u30ec\u30f3\u30b9\u3078\u306e\u8ad6\u6587\u63a1\u629e\u306b\u5411\u3051\u3066\uff08NLP\u7814\u7a76\u5206\u91ce\u7248\uff09<\/a>
\n\u30fb\u7814\u7a76\u306b\u304a\u3051\u308b\u8a55\u4fa1\u5b9f\u9a13\u3067\u91cd\u8981\u306a7\u3064\u306e\u3053\u3068<\/a>
\n\u30fb\u677e\u5c3e\u3050\u307f\u306e\u8ad6\u6587\u306e\u66f8\u304d\u65b9\uff1a\u82f1\u8a9e\u8ad6\u6587<\/a><\/p>\n

\u30fbPapers with code<\/a>
\n\u30fbHugging Face<\/a>
\n\u30fbDistill<\/a>
\n\u30fblabml.ai Deep Learning Paper Implementations<\/a>
\n\u30fbPyTorch Image Models<\/a><\/p>\n

\u30fbHow PyTorch Transposed Conv1D Work<\/a>
\n\u30fbDeconvolution and Checkerboard Artifacts<\/a>
\n\u30fbFlow-based Deep Generative Models<\/a>
\n\u30fblearn2learn<\/a><\/p>\n

\u30fb\u5b89\u6613\u306b\u9006\u884c\u5217\u3092\u8a08\u7b97\u3059\u308b\u306e\u306f\u3084\u3081\u3088\u3046<\/a>
\n\u30fb\u6709\u540d\u4f01\u696d\u306e\u30a8\u30f3\u30b8\u30cb\u30a2\u5411\u3051\u7814\u4fee\u8cc7\u6599\u307e\u3068\u3081<\/a><\/p>\n

\u3010General\u3011
\n\u30fbReal-ESRGAN-GUI<\/a>
\n\u30fbTorchOpt<\/a><\/p>\n

\u3010Transformer\u95a2\u9023\u3011
\n\u30fbTransformer Language Model Mathematical Definition<\/a>
\n\u30fb\u3088\u308a\u826f\u3044transformer\u3092\u3064\u304f\u308b<\/a>
\n\u30fbTransformer\u306e\u6700\u524d\u7dda \uff5e \u7573\u8fbc\u307f\u30cb\u30e5\u30fc\u30e9\u30eb\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u306e\u5148\u3078 \uff5e<\/a>
\n\u30fb\u3010\u30e1\u30bf\u30b5\u30fc\u30d9\u30a4\u3011Transformer\u304b\u3089\u57fa\u76e4\u30e2\u30c7\u30eb\u307e\u3067\u306e\u6d41\u308c<\/a>
\n\u30fbTransformer \u30e1\u30bf\u30b5\u30fc\u30d9\u30a4<\/a><\/p>\n

\u3010Flow-based Model\u3011
\n\u30fbNormalizing Flow\u5165\u9580 \u7b2c1\u56de \u5909\u5206\u63a8\u8ad6<\/a>
\n\u30fbNormalizing Flow\u5165\u9580 \u7b2c2\u56de Planar Flow<\/a>
\n\u30fbNormalizing Flow\u5165\u9580 \u7b2c3\u56de Bijective Coupling<\/a>
\n\u30fbNormalizing Flow\u5165\u9580 \u7b2c4\u56de Glow<\/a>
\n\u30fbNormalizing Flow\u5165\u9580 \u7b2c5\u56de Autoregressive Flow<\/a>
\n\u30fbNormalizing Flow\u5165\u9580 \u7b2c6\u56de Residual Flow<\/a>
\n\u30fbNormalizing Flow\u5165\u9580 \u7b2c7\u56de Neural ODE\u3068FFJORD<\/a><\/p>\n

\u30fbVariational Inference with Normalizing Flows<\/a>
\n\u30fbNICE: Non-linear Independent Components Estimation<\/a>
\n\u30fbDensity estimation using Real NVP<\/a>
\n\u30fbGlow: Generative Flow with Invertible 1×1 Convolutions<\/a><\/p>\n

\u3010Diffusion Model\u3011
\n\u30fbAwesome Diffusion Models<\/a>
\n\u30fbDenoising Diffusion Probabilistic Models (DDPM)<\/a>
\n\u30fbUnderstanding Diffusion Models: A Unified Perspective<\/a>
\n\u30fbGenerative Modeling by Estimating Gradients of the Data Distribution<\/a>
\n\u30fbInject Noise to Remove Noise: A Deep Dive into Score-Based Generative Modeling Techniques<\/a><\/p>\n

 <\/p>\n

\u3010GAN\u95a2\u9023\u3011
\n\u30fbLarge Scale GAN Training for High Fidelity Natural Image Synthesis<\/a>
\n\u30fbA Style-Based Generator Architecture for Generative Adversarial Networks<\/a>
\n\u30fbHoloGAN: Unsupervised Learning of 3D Representations from Natural Images<\/a>
\n\u30fbFew-Shot Adversarial Learning of Realistic Neural Talking Head Models<\/a>
\n\u30fbSinGAN: Learning a Generative Model from a Single Natural Image<\/a>
\n\u30fbTowards a Deeper Understanding of Adversarial Losses under a Discriminative Adversarial Network Setting<\/a><\/p>\n

\u25cfGenerative Adversarial Networks
\n\u30fbGenerative Adversarial Nets<\/a>
\n\u25cfBiGAN, ALI
\n\u30fbAdversarial Feature Learning<\/a>
\n\u30fbAdversarially Learned Inference<\/a>
\n\u30fbAdversarially Learned Inference – GitHub Pages<\/a>
\n\u25cfVAE-GAN
\n\u30fbAutoencoding beyond pixels using a learned similarity metric<\/a>
\n\u25cfAdversarial Autoencoder
\n\u30fbAdversarial Autoencoders<\/a>
\n\u25cfWasserstein GAN
\n\u30fbWasserstein GAN<\/a>
\n\u25cfGradient Penalty
\n\u30fbImproved Training Wasserstein GANs<\/a>
\n\u25cfPerceptual Loss
\n\u30fbPerceptual Loss for Real-Time Style Transfer and Super-Resolution<\/a>
\n\u25cfHinge Loss
\n\u30fbHierarchical Implicit Models and Likelihood-Free Variational Inference<\/a> Tran, Ranganath, Blei, 2017
\n\u30fbGeometric GAN<\/a> Lim & Ye, 2017
\n\u30fbSpectral Normalization for Generative Adversarial Networks<\/a> Miyato, Kataoka, Koyama, Yoshida, 2018
\n\u25cfFeature Matching Loss
\n\u30fbHigh-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs<\/a>
\n\u25cfInstance Normalization
\n\u30fbInstance Normalization: The Missing Ingredient for Fast Stylization<\/a>
\n\u25cfSpectral Normalization
\n\u30fbSpectral Normalization for Generative Adversarial Networks<\/a>
\n\u25cfAdaptive Instance Normalization(AdaIN)
\n\u30fbArbitrary Style Transfer in Real-time with Adaptive Instance Normalization<\/a>
\n\u25cfSelf-Attention
\n\u30fbSelf-Attention Generative Adversarial Networks<\/a>
\n\u25cfProjection Discriminator
\n\u30fbcGANs with Projection Discriminator<\/a>
\n\u25cfInception Score
\n\u30fbImproved Techniques for Training GANs<\/a>
\n\u25cfFrechet-Inception Distance(FID)
\n\u30fbGANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium<\/a>
\n\u25cfStructured Similarity(SSIM)
\n\u30fbImage Quality Assessment: From Error Visibility to Structural Similarity<\/a>
\n\u25cfPerception-Distortion Tradeoff
\n\u30fbThe Perception-Distortion Tradeoff<\/a>
\n\u25cfCosine Similarity(CSIM)
\n\u30fbArcFace: Additive Angular Margin Loss for Deep Face Recognition<\/a><\/p>\n

\u3010Meta Learning\u3011
\nMeta-Learning: Learning to Learn Fast – Lil’Log<\/a>
\nFew-shot Learning\u3068\u306f\u4f55\u306a\u306e\u304b\u3010Generalizing from a few examples: A survey on few-shot learning\u3011<\/a>
\n\u30fbMetaGAN: An Adversarial Approach to Few-Shot Learning<\/a>
\n\u25cfMAML
\n\u30fbModel-Agnostic Meta-Learning For Fast Adaptation of Deep Neural Networks<\/a>
\n\u25cfReptile (FOMAML)
\n\u30fbOn First-Order Meta-Learning Algorithims<\/a>
\n\u25cfImplicit MAML
\n\u30fbMeta-Learning with Implicit Graidents<\/a>
\n\u30fbModular Meta-Learning with Shrinkage<\/a>
\n\u25cfCAVIA
\n\u30fbFast Context Adaptation via Meta-Learning<\/a>
\n\u25cfTAML
\n\u30fbTask-Agnostic Meta-Learning for Few-shot Learning<\/a><\/p>\n

\u3010The Lottery Ticket Hypothesis\u3011
\n\u30fbThe Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks<\/a>
\n\u30fbWhat’s Hidden in a Randomly Weighted Neural Network?<\/a>
\n\u30fbTraining BatchNorm and Only BatchNorm: On the Expressive Power of Random Feature in CNNs<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

\u3010Tips\u3011 \u30fbdlbook_notation \u30fbFormatting Inst … <\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-22088","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/blog.yokokanno.com\/index.php?rest_route=\/wp\/v2\/pages\/22088","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.yokokanno.com\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/blog.yokokanno.com\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/blog.yokokanno.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.yokokanno.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=22088"}],"version-history":[{"count":37,"href":"https:\/\/blog.yokokanno.com\/index.php?rest_route=\/wp\/v2\/pages\/22088\/revisions"}],"predecessor-version":[{"id":22669,"href":"https:\/\/blog.yokokanno.com\/index.php?rest_route=\/wp\/v2\/pages\/22088\/revisions\/22669"}],"wp:attachment":[{"href":"https:\/\/blog.yokokanno.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=22088"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}