| 1 |
NN一般 |
takagi |
https://arxiv.org/abs/1710.09829 |
Dynamic Routing Between Capsules |
capsule net |
|
強化学習 |
@kmiwa |
https://arxiv.org/abs/1803.04675 |
Using Grouped Linear Prediction and Accelerated Reinforcement Learning for Online Content Caching |
|
|
自然言語 チャットボット |
@nharu1san |
https://arxiv.org/abs/1612.01627 |
Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots |
|
|
教育 |
@kaaztech |
https://dl.acm.org/doi/10.1145/3027385.3029479 |
A neural network approach for students' performance prediction |
|
|
NN一般 活性化 |
@antimon2 |
https://arxiv.org/abs/1710.05941 |
Searching for Activation Functions |
swish |
|
アノテーション 医療 |
@exoego |
https://arxiv.org/abs/1708.06297 |
Employing Weak Annotations for Medical Image Analysis Problems |
|
|
量子化 |
@cohama |
https://arxiv.org/abs/1511.00363 |
BinaryConnect: Training Deep Neural Networks with binary weights during propagations |
|
|
正規化 |
@melleo1978 |
https://arxiv.org/abs/1705.08741 |
Train longer, generalize better: closing the generalization gap in large batch training of neural networks |
ghost batch normalization |
|
ドメイン適用 |
@kotamatui |
http://papers.nips.cc/paper/6963-joint-distribution-optimal-transportation-for-domain-adaptation.pdf |
Joint distribution optimal transportation for domain adaptation |
|
|
物体検出 zero_shot |
@n-kats |
https://arxiv.org/abs/1803.06049 |
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concept |
|
| 2 |
自然言語 |
@nharu1san |
https://arxiv.org/abs/1802.02614v1 |
Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus |
|
|
敵対的事例 |
@antimon2 |
https://arxiv.org/abs/1804.00499 |
Semantic Adversarial Examples |
|
|
強化学習 |
@kmiwa |
https://arxiv.org/abs/1603.00748 |
Continuous Deep Q-Learning with Model-based Acceleration |
|
|
物体検出 |
@n-kats |
https://arxiv.org/abs/1712.00960 |
FSSD: Feature Fusion Single Shot Multibox Detector |
|
|
工場 |
sakurai |
https://ieeexplore.ieee.org/document/7864335 |
A Generic Deep-Learning-Based Approach for Automated Surface Inspection |
|
| 3 |
半教師 |
@antimon2 |
https://arxiv.org/abs/1805.09302 |
Input and Weight Space Smoothing for Semi-supervised Learning |
|
|
Pruning |
@cohama |
https://arxiv.org/abs/1805.11394 |
A novel channel pruning method for deep neural network compression |
|
|
GAN 顔 |
@yunishimura |
https://www.jstage.jst.go.jp/articleke/advpub/0/advpub_TJSKE-D-17-00085/_pdf/-char/ja |
Face Image Generation System using Attributes Information with DCGANs |
|
|
学習率スケジューリング |
@wkluk-hk |
https://arxiv.org/abs/1506.01186v6 |
Cyclical Learning Rates for Training Neural Networks |
|
|
工場 |
sakurai |
http://journals.sagepub.com/doi/pdf/10.1177/1687814018766682 |
Intelligent defect classification system based on deep learning |
|
|
3D SLAM |
@melleo1978 |
https://arxiv.org/abs/1803.02286 |
Learning monocular visual odometry with dense 3D mapping from dense 3D flow |
|
|
強化学習 |
@kmiwa |
https://arxiv.org/abs/1804.00379 |
Recall Traces: Backtracking Models for Efficient Reinforcement Learning |
|
|
GAN attention |
@n-kats |
https://arxiv.org/abs/1805.0831 |
Self-Attention Generative Adversarial Networks |
SAGAN |
|
自然言語 文書埋め込み |
@nharu1san |
https://arxiv.org/abs/1803.11175 |
Universal Sentence Encoder |
|
| 4 |
トラッキング MOT |
@wkluk-hk |
https://arxiv.org/abs/1711.02741 |
Recurrent Autoregressive Networks for Online Multi-Object Tracking |
|
|
GAN |
takagi |
https://arxiv.org/abs/1702.08431 |
Boundary-Seeking Generative Adversarial Networks |
|
|
ライブラリ |
@cohama |
https://arxiv.org/abs/1410.0759 |
cuDNN: Efficient Primitives for Deep Learning |
cuDNN |
|
キャプション生成 |
@Denpa92 |
https://arxiv.org/abs/1806.04510 |
Dank Learning: Generating Memes Using Deep Neural Networks |
|
|
自然言語 構文 |
@nharu1san |
http://www.aclweb.org/anthology/P15-1162 |
Deep Unordered Composition Rivals Syntactic Methods for Text Classification |
|
|
強化学習 関係 |
@kmiwa |
https://arxiv.org/abs/1806.01830 |
Relational Deep Reinforcement Learning |
|
|
強化学習 |
@shuuichi |
https://arxiv.org/abs/1803.07055 |
Simple random search provides a competitive approachto reinforcement learning |
|
|
強化学習 |
@antimon2 |
https://arxiv.org/abs/1806.00175 |
Strategic Object Oriented Reinforcement Learning |
|
|
転移学習 |
sakurai |
https://ieeexplore.ieee.org/document/7966162 |
Transfer Learning for Automated Optical Inspection |
|
|
GAN 音 |
@hissanova |
https://arxiv.org/abs/1802.04208 |
Synthesizing Audio with Generative Adversarial Networks |
|
|
GAN |
@n-kats |
https://arxiv.org/abs/1709.01118 |
WESPE: Weakly Supervised Photo Enhancer for Digital Cameras |
|
| 6 |
インスタンスセグメンテーション |
@wkluk-hk |
https://arxiv.org/abs/1807.05361 |
Non-local RoIs for Instance Segmentation |
|
|
フロー系生成モデル |
@antimon2 |
https://arxiv.org/abs/1807.03039 |
Glow: Generative Flow with Invertible 1×1 Convolutions |
Glow |
|
強化学習 |
@kmiwa |
https://arxiv.org/abs/1802.03006 |
Learning and Querying Fast Generative Models for Reinforcement Learnin |
|
|
ライブラリ |
@kencyke |
http://www.kdd.org/kdd2017/papers/view/tfx-a-tensorflow-based-production-scale-machine-learning-platform |
TFX: A TensorFlow-Based Production-Scale Machine Learning Platform |
TFX |
|
NN一般 初期化 |
@melleo1978 |
https://arxiv.org/abs/1702.08591 |
The Shattered Gradients Problem: If resnets are the answer, then what is the question? |
|
|
画像データセット |
@yuji38kwmt |
https://www.arxiv-vanity.com/papers/1805.04687/ |
BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling |
BDD100K |
|
グラフ系 |
@n-kats |
https://arxiv.org/abs/1806.01261 |
Relational inductive biases, deep learning, and graph networks |
GN |
|
強化学習 |
@kmiwa |
https://arxiv.org/pdf/1707.06203 |
Imagination-Augmented Agents for Deep Reinforcement Learning |
|
|
自然言語データセット |
@nharu1san |
https://arxiv.org/abs/1312.3005 |
One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling |
|
|
転移学習 |
sakurai |
https://arxiv.org/abs/1805.08974 |
Do Better ImageNet Models Transfer Better ? |
|
| 7 |
対話 |
takagi |
https://www.jstage.jst.go.jp/article/tjsai/33/1/33_DSH-F/_pdf |
Engagement Recognition from Listener’s Behaviors in Spoken Dialogue Using a Latent Character Model |
|
|
蒸留 |
yasuno |
http://export.arxiv.org/pdf/1805.04770 |
Born Again Neural Networks |
|
|
アノテーション |
@yuji38kwmt |
https://arxiv.org/abs/1809.08888 |
Empirical Methodology for Crowdsourcing Ground Truth |
|
|
物体検出 |
@n-kats |
https://arxiv.org/abs/1711.07240 |
MegDet: A Large Mini-Batch Object Detector |
MegDet |
|
軽量モデル |
@cohama |
https://arxiv.org/abs/1807.11164 |
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design |
ShuffleNet V2 |
|
NN一般 活性化 |
@antimon2 |
https://arxiv.org/abs/1810.01829 |
Weighted Sigmoid Gate Unit for an Activation Function of Deep Neural Network |
|
| 8 |
理論 NN一般 初期化 |
@melleo1978 |
https://arxiv.org/abs/1806.05393v2 |
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks |
|
|
インスタンスセグメンテーション 点群 医療 |
@wkluk-hk |
https://arxiv.org/abs/1811.03208 |
Deep Semantic Instance Segmentation of Tree-like Structures Using Synthetic Data |
|
|
ライブラリ |
@antimon2 |
https://arxiv.org/abs/1810.09868 |
Automatic Full Compilation of Julia Programs and ML Models to Cloud TPUs |
|
|
3D |
@n-kats |
https://arxiv.org/abs/1804.01654 |
Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images |
|
|
軽量モデル |
@cohama |
http://openaccess.thecvf.com/content_ECCV_2018/html/Xin_Wang_SkipNet_Learning_Dynamic_ECCV_2018_paper.html |
SkipNet: Learning Dynamic Routing in Convolutional Networks |
|
|
画像データセット アノテーション |
@yuji38kwmt |
https://arxiv.org/abs/1712.08394 |
The ParallelEye Dataset: Constructing Large-Scale Artificial Scenes for Traffic Vision Research |
|
|
神経科学 |
@nharu1san |
https://arxiv.org/abs/1811.02923 |
Universal Spike Classifier |
|
| 9 |
量子化 |
@melleo1978 |
https://openreview.net/forum?id=ByfPDyrYim |
Linear Backprop in non-linear networks |
|
|
異常検知 |
@devjap |
https://arxiv.org/abs/1703.05921 |
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery |
|
|
アノテーション |
@yuji38kwmt |
https://www.researchgate.net/publication/291249011_Crowdsourcing_annotations_for_visual_object_detection |
Crowdsourcing Annotations for Visual Object Detection |
|
|
距離 最適輸送 |
@n-kats |
https://arxiv.org/abs/1811.02834 |
Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties |
|
|
転移学習 |
sakurai |
https://arxiv.org/abs/1808.01974 |
A Survey of Deep Transfer Learning |
|
|
NN一般 padding |
@antimon2 |
https://arxiv.org/abs/1811.11718 |
Partial Convolution based Padding |
|
|
軽量モデル NAS |
@cohama |
https://arxiv.org/abs/1812.02975 |
ShuffleNASNets: Efficient CNN models through modified Efficient Neural Architecture Search |
|
| 10 |
理論 正規化 |
@melleo1978 |
https://arxiv.org/abs/1805.11604v3 |
How Does Batch Normalization Help Optimization? |
|
|
対話 |
takagi |
http://www.cs.toronto.edu/face2face |
A face to face neural conversation model |
|
|
蒸留 転移学習 |
sakurai |
https://arxiv.org/abs/1503.02531 |
Distilling the Knowledge in a Neural Network |
|
|
物体検出 |
@cohama |
https://arxiv.org/abs/1804.06215 |
DetNet: A Backbone network for Object Detection |
|
|
運転 車線 |
@yuji38kwmt |
https://arxiv.org/abs/1806.05984 |
|
Ego-Lane Analysis System (ELAS): Dataset and Algorithms |
|
ライブラリ |
@antimon2 |
https://arxiv.org/abs/1812.09064 |
GaussianProcesses.jl: A Nonparametric Bayes package for the Julia Language |
|
|
3D SLAM |
@n-kats |
https://arxiv.org/abs/1811.06152 |
Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos |
|
| 11 |
GAN |
@melleo1978 |
https://arxiv.org/abs/1812.04948 |
A Style-Based Generator Architecture for Generative Adversarial Networks |
StyleGAN |
|
軽量モデル |
@cohama |
https://arxiv.org/abs/1901.09615 |
Convolutional Neural Networks with Layer Reuse |
|
|
NAS グラフ系 |
@n-kats |
https://arxiv.org/abs/1808.07233 |
Neural Architecture Optimization |
|
|
時系列 |
sakurai |
https://arxiv.org/abs/1811.01533 |
Transfer learning for time series classification |
|
| 12 |
ライブラリ |
@antimon2 |
https://arxiv.org/abs/1902.02376 |
DiffEqFlux.jl — A Julia Library for Neural Differential Equations |
|
|
自然言語 質問回答 |
@nharu1san |
https://arxiv.org/abs/1902.01718 |
End-to-End Open-Domain Question Answering with BERTserini |
|
|
軽量モデル |
@cohama |
https://arxiv.org/abs/1902.09701 |
Learning Implicitly Recurrent CNNs Through Parameter Sharing |
|
| 13 |
GAN 3D |
@melleo1978 |
https://arxiv.org/abs/1904.01326 |
HoloGAN: Unsupervised learning of 3D representations from natural images |
HoloGAN |
|
GAN |
takagi |
https://arxiv.org/abs/1811.10597v2 |
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks |
|
|
3D SLAM |
@n-kats |
https://arxiv.org/abs/1904.04998 |
Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras |
|
|
自然言語 文書分類 |
@nharu1san |
https://arxiv.org/abs/arxiv_1904.08398 |
DocBERT: BERT for Document Classification |
|
|
物体検出 |
@cohama |
https://arxiv.org/abs/1904.01355v3 |
FCOS: Fully Convolutional One-Stage Object Detection |
FCOS |
|
時系列 |
sakurai |
http://www.lumenai.fr/blog/time-series-aggregation |
Time series aggregation Comparison of two global averaging approaches |
|
|
運転 車線 |
@yuji38kwmt |
https://arxiv.org/abs/1802.05591 |
Towards End-to-End Lane Detection: an Instance Segmentation Approach |
|
| 14 |
NN一般 初期化 |
@melleo1978 |
https://arxiv.org/abs/1901.09321 |
Fixup Initialization: Residual Learning Without Normalization |
Fixup |
|
自然言語 |
@nharu1san |
https://arxiv.org/abs/1905.05950 |
BERT Rediscovers the Classical NLP Pipeline |
|
|
物体検出 |
@cohama |
https://arxiv.org/abs/1904.08189 |
CenterNet: Keypoint Triplets for Object Detection |
|
|
運転 |
@yuji38kwmt |
https://arxiv.org/abs/1904.08980 |
Exploring the Limitations of Behavior Cloning for Autonomous Driving |
|
|
インスタンスセグメンテーション |
@antimon2 |
https://arxiv.org/abs/1708.02551 |
Semantic Instance Segmentation with a Discriminative Loss Function |
|
|
3D |
@n-kats |
https://arxiv.org/abs/1812.03828 |
Occupancy Networks: Learning 3D Reconstruction in Function Space |
|
|
埋め込み 顔 |
takagi |
https://arxiv.org/abs/1811.11283 |
A Compact Embedding for Facial Expression Similarity |
|
| 15 |
半教師 |
@melleo1978 |
https://arxiv.org/abs/1904.12848v1 |
Unsupervised Data Augmentation |
|
|
強化学習 |
@Mit-Funa |
https://deepmind.com/blog/capture-the-flag-science/?utm_source=Deep+Learning+Weekly&utm_campaign=cf75ae36f6-EMAIL_CAMPAIGN_2019_04_24_03_18_COPY_01&utm_medium=email&utm_term=0_384567b42d-cf75ae36f6-73708453 |
Human-level performance in 3D multiplayer games with populationbased reinforcement learning |
|
|
半教師 |
@cohama |
https://arxiv.org/abs/1905.02249v1 |
MixMatch: A Holistic Approach to Semi-Supervised Learning |
MixMatch |
|
自然言語 司法 |
@nharu1san |
https://arxiv.org/abs/1906.02059 |
Neural Legal Judgment Prediction in English |
|
|
理論 |
@n-kats |
https://arxiv.org/abs/1805.08522 |
Deep learning generalizes because the parameter-function map is biased towards simple functions |
|
| 16 |
データオーグメント |
@melleo1978 |
https://arxiv.org/abs/1810.12890 |
DropBlock: A regularization method for convolutional networks |
|
|
最適化 |
@Kgm1500 |
https://arxiv.org/abs/1802.09568 |
Shampoo: Preconditioned Stochastic Tensor Optimization |
|
|
画風変換 |
@n-kats |
https://arxiv.org/abs/1703.06868 |
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization |
AdaIN |
|
NN一般 |
@cohama |
https://arxiv.org/abs/1703.06211 |
Deformable Convolutional Networks |
|
|
ライブラリ |
@antimon2 |
https://estadistika.github.io//julia/python/packages/knet/flux/tensorflow/machine-learning/deep-learning/2019/06/20/Deep-Learning-Exploring-High-Level-APIs-of-Knet.jl-and-Flux.jl-in-comparison-to-Tensorflow-Keras.html |
Deep Learning: Exploring High Level APIs of Knet.jl and Flux.jl in comparison to Tensorflow-Keras |
|
|
強化学習環境 |
@Mit-Funa |
https://ai.googleblog.com/2019/06/introducing-google-research-football.html |
Google Research Football: A Novel Reinforcement Learning Environment |
|
| 17 |
最適化 |
@melleo1978 |
https://arxiv.org/abs/1905.11286 |
Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks |
NovoGrad |
|
自己教師 optical_flow |
@n-kats |
https://arxiv.org/abs/1904.09117 |
SelFlow: Self-Supervised Learning of Optical Flow |
|
|
自己教師 トラッキング |
@cohama |
https://arxiv.org/abs/1806.09594 |
Tracking Emerges by Colorizing Videos |
|
| 18 |
attention |
@melleo1978 |
https://arxiv.org/abs/1906.05909 |
Stand-Alone Self-Attention in Vision Models |
|
|
物体検出 |
@cohama |
https://arxiv.org/abs/1909.03625 |
CBNet: A Novel Composite Backbone Network Architecture for Object Detection |
|
|
グラフ系 物理 |
@n-kats |
https://arxiv.org/abs/1909.02487 |
Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks |
FermiNet |
|
ライブラリ |
@antimon2 |
https://dl.acm.org/inst_page.cfm?id=60022195 |
Gen: A General-Purpose Probabilistic Programming System with Programmable Inference |
|
|
グラフ系 物理 |
@yuji38kwmt |
https://arxiv.org/abs/1906.10033 |
Unifying machine learning and quantum chemistry – a deep neural network for molecular wavefunctions |
|
| 19 |
tutorial |
@FunabikiKeisuke |
https://arxiv.org/abs/1909.13739 |
https://www.programiz.com/python-programming |
|
|
フロー系生成 グラフ系 物理 |
@n-kats |
https://arxiv.org/abs/1909.13739 |
Equivariant Hamiltonian Flows |
|
| 20 |
contrastive_learning |
@melleo1978 |
https://arxiv.org/abs/1911.05722v2 |
Momentum Contrast for Unsupervised Visual Representation Learning |
MoCo |
|
異常検知 |
@wkluk-hk |
https://arxiv.org/abs/1802.06222 |
Efficient GAN-Based Anomaly Detection |
|
|
自然言語 |
@nharu1san |
https://arxiv.org/abs/1910.13461 |
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension |
|
|
動画生成 姿勢 |
@n-kats |
https://arxiv.org/abs/1910.12713 |
Few-shot Video-to-Video Synthesis |
|
|
アノテーション |
@yuji38kwmt |
https://arxiv.org/abs/1911.02807 |
Improving Human Annotation in Single Object Tracking |
|
|
物体検出 |
@cohama |
https://arxiv.org/abs/1901.01892 |
Scale-Aware Trident Networks for Object Detection |
|
| 21 |
GAN |
@melleo1978 |
https://arxiv.org/abs/1912.04958 |
Analyzing and Improving the Image Quality of StyleGAN |
StyleGAN2 |
|
NAS |
@wkluk-hk |
https://arxiv.org/abs/1807.11626 |
MnasNet: Platform-Aware Neural Architecture Search for Mobile |
MNAS |
|
強化学習 |
@Mit-Funa |
https://arxiv.org/abs/1912.00167 |
IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks |
|
|
検索 |
@yuji38kwmt |
https://arxiv.org/abs/1903.04638 |
Challenges in Search on Streaming Services: Netflix Case Study |
|
|
NN一般 |
@n-kats |
https://arxiv.org/abs/1905.11786 |
Putting An End to End-to-End: Gradient-Isolated Learning of Representations |
GIM |
|
ライブラリ SLAM |
@nharu1san |
https://arxiv.org/abs/1910.01122 |
OpenVSLAM: A Versatile Visual SLAM Framework |
OpenVSLAM |
|
ライブラリ |
@cohama |
https://www.atmarkit.co.jp/ait/articles/1910/31/news028.html |
PyTorch vs. TensorFlow |
|
| 22 |
画像データセット アノテーション 運転 キャプション |
@melleo1978 |
https://arxiv.org/abs/1807.11546 |
Textual Explanations for Self-Driving Vehicles |
BDD-X |
|
データ 転移学習 |
@wkluk-hk |
https://arxiv.org/abs/2001.02799 |
Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data |
|
|
3D |
@antimon2 |
https://arxiv.org/abs/2001.05422 |
Indoor Layout Estimation by 2D LiDAR and Camera Fusion |
|
|
強化学習 |
@n-kats |
https://arxiv.org/abs/1911.08265 |
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model |
MuZero |
|
ライブラリ エッジ |
@Mit-Funa |
https://github.com/NNgen/nngen |
NNgen |
|
| 23 |
contrastive_learning |
@melleo1978 |
https://arxiv.org/abs/2002.05709 |
A Simple Framework for Contrastive Learning of Visual Representations |
SimCLR |
|
セグメンテーション |
@FunabikiKeisuke |
http://mprg.jp/data/MPRG/F_group/F20191205_goto.pdf |
カメラ間の整合性を考慮した全周囲画像のセグメンテーション |
|
|
強化学習 |
@Mit-Funa |
https://arxiv.org/abs/1806.06923 |
Implicit Quantile Networks for Distributional Reinforcement Learning |
|
|
アノテーション |
@yuji38kwmt |
https://arxiv.org/abs/2002.06626 |
Block Annotation: Better Image Annotation for Semantic Segmentation with Sub-Image Decomposition |
|
|
理論 蒸留 |
@n-kats |
https://arxiv.org/abs/2002.05715 |
Self-Distillation Amplifies Regularization in Hilbert Space |
|
|
物体検出 |
@cohama |
https://arxiv.org/abs/1911.12451v3 |
Empirical Upper Bound in Object Detection and More |
|
| 24 |
3D SLAM |
@melleo1978 |
https://arxiv.org/abs/2002.05709 |
Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry |
|
|
強化学習 world_model |
@Mit-Funa |
https://ai.googleblog.com/2020/03/introducing-dreamer-scalable.html?m=1 |
Introducing Dreamer: Scalable Reinforcement Learning Using World Models |
|
|
物体検出 レア事例 |
@cohama |
https://arxiv.org/abs/2003.05176 |
Equalization Loss for Long-Tailed Object Recognition |
|
|
NN一般 正規化 |
@n-kats |
https://arxiv.org/abs/2002.10444 |
Batch Normalization Biases Deep Residual Networks Towards Shallow Paths |
Skip init |
| 25 |
3D |
@strshp |
https://drive.google.com/file/d/17ki_YAL1k5CaHHP3pIBFWvw-ztF4CCPP/view |
3D Photography using Context-aware Layered Depth Inpainting |
|
|
高速化 |
@melleo1978 |
https://arxiv.org/abs/1903.03129v2 |
SLIDE : IN DEFENSE OF SMART ALGORITHMS OVER HARDWARE ACCELERATION FOR LARGE-SCALE DEEP LEARNING SYSTEMS |
SLIDE |
|
VAE |
@sennin0901 |
https://arxiv.org/abs/1906.00446 |
Generating Diverse High-Fidelity Images with VQ-VAE-2 |
VQ-VAE-2 |
|
3D グラフ系 点群 インスタンスセグメンテーション |
@n-kats |
https://arxiv.org/abs/2003.13867 |
3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation |
|
|
NN一般 軽量モデル |
@cohama |
https://arxiv.org/abs/2003.13549v2 |
Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets |
BSConv |
|
アノテーション |
@usakotail |
https://www.arxiv-vanity.com/papers/1909.12493/ |
Invisible Marker:Automatic Annotation for Object Manipulation |
|
| 26 |
GAN 姿勢 |
@strshp |
https://menyifang.github.io/projects/ADGAN/ADGAN_files/Paper_ADGAN_CVPR2020.pdf |
Controllable Person Image Synthesis with Attribute-Decomposed GAN |
|
|
GAN auto_encoder |
@sennin0901 |
https://arxiv.org/abs/2004.04467 |
Adversarial Latent Autoencoders |
|
|
最適化 |
@melleo1978 |
https://arxiv.org/abs/2001.06782v2 |
Gradient Surgery for Multi-Task Learning |
|
|
contrastive_learning world_model |
@n-kats |
https://arxiv.org/abs/1911.12247 |
Contrastive Learning of Structured World Models |
C-SWM |
|
NN一般 正規化 |
@cohama |
https://arxiv.org/abs/1905.11926v4 |
Network Deconvolution |
|
|
物体検出 |
@usakotail |
https://arxiv.org/abs/2004.10934 |
YOLOv4: Optimal Speed and Accuracy of Object Detection |
YOLOv4 |
| 27 |
物体検出 |
@n-kats |
https://arxiv.org/abs/2005.12872 |
End-to-End Object Detection with Transformers |
DETR |
|
物体検出 |
@cohama |
https://arxiv.org/abs/2006.04388v1 |
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection |
Gemeralized fOcal loss |
|
因果推論 |
@K_Ryuichirou |
https://www.pnas.org/content/116/10/4156 |
Metalearners for estimating heterogeneous treatment effects using machine learning |
|
|
GAN ファッション |
@usakotail |
https://openaccess.thecvf.com/content_CVPR_2020/html/Neuberger_Image_Based_Virtual_Try-On_Network_From_Unpaired_Data_CVPR_2020_paper.html |
Image Based Virtual Try-on Network from Unpaired Data |
|
|
contrastive_learning 自己教師 |
@melleo1978 |
https://arxiv.org/abs/2006.07733v1 |
Bootstrap Your Own Latent A New Approach to Self-Supervised Learning |
BYOL |
| 28 |
教師ノイズ |
@cohama |
https://arxiv.org/abs/1910.00701 |
Distilling Effective Supervision from Severe Label Noise |
|
|
自然言語 |
@n-kats |
https://arxiv.org/abs/2006.16236 |
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention |
|
|
点群 |
@usakotail |
https://arxiv.org/abs/1612.00593 |
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation |
PointNet |
|
contrastive_learning 自己教師 |
@melleo1978 |
https://arxiv.org/abs/2005.04966v2 |
Prototypical Contrastive Learning of Unsupervised Representations |
|
|
インスタンスセグメンテーション トラッキング |
@sennin0901 |
https://arxiv.org/abs/1912.04573 |
Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation |
|
| 29 |
強化学習 |
@Mit-Funa |
https://arxiv.org/abs/1909.01387 |
Making Efficient Use ofDemonstrations to Solve Hard Exploration Problems |
R2D3 |
|
3D |
@n-kats |
https://arxiv.org/abs/1909.01387 |
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections |
NeRF-W |
|
アノテーション インスタンスセグメンテーション |
@strshp |
https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/495_ECCV_2020_paper.php |
PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click |
PhraseClick |
|
画像分類 |
@cohama |
https://arxiv.org/abs/2007.09558 |
Resolution Switchable Networks for Runtime Efficient Image Recognition |
|
|
3D |
@melleo1978 |
https://arxiv.org/abs/2003.10432v2 |
Atlas: End-to-End 3D Scene Reconstruction from Posed Images |
Atlas |