https://www.youtube.com/playlist?list=PLXiK3f5MOQ760xYLb2eWbtOKOwUC-bByj
- Generative adversarial nets
- Deformable Convolutional Networks
- Learning phrase representations using RNN encoder-decoder for statistical machine translation
- Image Super-Resolution Using Deep Convolutional Networks
- Playing Atari with Deep Reinforcement Learning (NIPS 2013 Deep Learning Workshop)
- Neural Turing Machine
- Deep Photo Style Transfer
- -
- Distilling the Knowledge in a Neural Network
- Auto-Encoding Variational Bayes, ICLR 2014
- Spatial Transformer Networks
- Faster R-CNN : Towards Real-Time Object Detection with Region Proposal Networks
- Domain Adversarial Training of Neural Network
- On Human Motion Prediction using RNNs (2017)
- Convolutional Neural Networks for Sentence Classification
- YOLO : You only look once: Unified, real-time object detection
- Neural Architecture Search with Reinforcement Learning
- A Simple Neural Network Module for Relational Reasoning (DeepMind)
- Continuous Control with Deep Reinforcement Learning
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Batch Normalization
- InfoGAN (openAI)
- YOLO9000: Better, Faster, Stronger
- Pixel Recurrent Neural Network
- Learning with side information through modality hallucination (2016)
- Notes for CVPR Machine Learning Session
- GloVe - Global vectors for word representation
- Densely Connected Convolutional Networks (CVPR 2017, Best Paper Award) by Gao Huang et al.
- Apprenticeship Learning via Inverse Reinforcement Learning
- Photo-Realistic Single Image Super Resolution Using a Generative Adversarial Network
- Learning to learn by gradient descent by gradient descent
- Deep Visual-Semantic Alignments for Generating Image Descriptions
- PVANet: Lightweight Deep Neural Networks for Real-time Object Detection
- Inception and Xception
- Understanding Black-box Predictions via Influence Functions (2017)
- Learning to Remember Rare Events
- Ask me anything: Dynamic memory networks for natural language processing
- Explaining and Harnessing Adversarial Examples
- Dropout as a Bayesian approximation
- WaveNet - A Generative Model for Raw Audio
- Show and Tell: A Neural Image Caption Generator
- Adam: A Method for Stochastic Optimization
- HyperNetworks
- MobileNet
- DeepLab: Semantic Image Segmentation
- Deep Knowledge Tracing
- Learning Deep Features for Discriminative Localization
- Towards Principled Methods for Training Generative Adversarial Networks
- Attention is All You Need
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Conditional Generative Adversarial Nets
- -
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
- Neural Machine Translation by Jointly Learning to Align and Translate
- Capsule Network
- Mask R-CNN
- The Consciousness Prior
- Style Transfer from Non-Parallel Text by Cross-Alignment
- Deep Neural Networks for YouTube Recommendations
- Understanding Deep Learning Requires Rethinking Generalization
- Deep Learning: A Critical Appraisal (2018)
- Peephole: Predicting Network Performance Before Training
- Wide&Deep Learning for Recommender Systems
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
- Don't decay the learning rate, increase the batch size
- Audio Super Resolution using Neural Nets
- DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
- Efficient Neural Architecture Search via Parameter Sharing
- SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud
- Categorical Reparameterization with Gumbel Softmax
- Deep Compression
- Generative Semantic Manipulation with Contrasting GAN
- ObamaNet: Photo-realistic lip-sync from text
- On Calibration of Modern Neural Networks (2017)
- Distributed Representations of Sentences and Documents
- SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
- Net2Net: Accelerating Learning via Knowledge Transfer
- Synthesizing Audio with Generative Adversarial Networks
- Practical Bayesian Optimization of Machine Learning Algorithms
- -
- Introduction to Speech Separation
- Non-local Neural Networks
- MegDet: A Large Mini-Batch Object Detector (CVPR2018)
- In-Datacenter Performance Analysis of a Tensor Processing Unit
- Curriculum Learning
- Spectral Normalization for Generative Adversarial Networks
- Deep Variational Bayes Filters (2017)
- Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
- Representation Learning by Learning to Count
- A Universal Music Translation Network
- Distributed Training of Neural Networks
- -
- Model-Agnostic Meta-Learning for fast adaptation of deep networks
- Modularity Matters: Learning Invariant Relational Reasoning Tasks
- Taskonomy: Disentangling Task Transfer Learning
- Learning Representations for Counterfactual Inference
- MegaDepth: Learning Single-View Depth Prediction from Internet Photos (CVPR2018)
- MRNet-Product2Vec
- SeedNet
- Deep Feature Consistent Variational Autoencoder
- Everybody Dance Now
- Visualizing Data using t-SNE
- Video-to-Video synthesis
- MnasNet: Platform-Aware Neural Architecture Search for Mobile
- Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
- Image Inpainting for Irregular Holes Using Partial Convolutions
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- An Analysis of Scale Invariance in Object Detection – SNIP
- EVA2:Exploiting Temporal Redundancy in Live Computer Vision
- Independent Component Analysis by Jae Duk Seo
- The Perception Distortion Tradeoff
- Recycle-GAN, Unsupervised Video Retargeting
- Unsupervised Anomaly Detection with Generative Adversarial Networks
- -
- PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
- Black-Box Attacks with Limited Queries and Information
- Active Learning For Convolutional Neural Networks: A Core-Set Approach
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- CAN: Creative Adversarial Networks
- Partial Convolution based Padding
- stacked denoising autoencoders
- ENERGY-BASED GENERATIVE ADVERSARIAL NETWORKS
- DensePose: Dense Human Pose Estimation In The Wild
- FaceNet
- TimbreTron: A Wavenet(CycleGAN(CQT(Audio))) pipeline for musical timbre transfer
- Horovod: fast and easy distributed deep learning in TensorFlow
- Generative Adversarial Imitation Learning
- A Style-Based Generator Architecture for Generative Adversarial Networks
- SSD: Single Shot MultiBox Detector
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- How Does Batch Normalization Help Optimization?
- Photo Wake-Up: 3D Character Animation from a Single Photo
- Self-Supervised Generative Adversarial Networks
- -
- Mixture Density Network
- Fully Convolutional Siamese Networks for Object Tracking
- Training Set Debugging Using Trusted Items
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
- Wasserstein GAN
- Recurrent World Models Facilitate Policy Evolution
- SqueezeNext: Hardware-Aware Neural Network Design
- Language Models are Unsupervised Multitask Learners (OpenAI GPT-2)
- CornerNet: Detecting Objects as Paired Keypoints
- Learning Deep Structure-Preserving Image-Text Embeddings
- deep anomaly detection using geometric transformations
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution
- ImageNet-trained CNNs are Biased Towards Textures
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
- SNAIL: A Simple Neural Attentive Meta-Learner
- Semantic Image Synthesis with Spatially-Adaptive Normalization
- Exploring Randomly Wired Neural Networks for Image Recognition
- ChannelNets: Compact and Efficient CNN via Channel-Wise Convolutions
- Bast of both worlds: human-machine collaboration for object annotation
- FOTS: Fast Oriented Text Sptting with a Unified Network
- SIFA: Towards Cross- Modality Domain Adaptation for Medical Image Segmentation
- BLoMo UnSupervised Learning of Transferable Relational Graph
- Transformer-XL: Attentive language Models Beyond a Fixed-Length Context
- FOTS: Fast Oriented Text Spotting with a Unified Network
- DeepPermNet: Visual Permutation Learning
- CNN Attention Networks
- InfoVAE: Balancing Learning and Inference in Variational Autoencoders
- Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
- Interpretability Beyond Feature Attribution: Testing with Concept Activation Vector (TCAV)
- Few Shot Unsupervised Image to Image Translation
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- ResNet - Deep Residual Learning for Image Recognition
- Large margin softmax loss for Convolutional Neural Networks
- Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
- Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
- Restricted Boltzmann Machine and Deep Belief Networks
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Combating Label Noise in Deep Learning using Abstention
- Framing U-Net via Deep Convolutional Framelets
- Graph Convolutional Network
- M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Data Shapley: Equitable Valuation of Data for Machine Learning
- Deep Learning Ensemble Method
- MixNet: Mixed Depthwise Convolutional Kernels
- And the Bit Goes Down: Revisiting the Quantization of Neural Networks
- RetinaFace: Single-stage Dense Face Localisation in the Wild
- Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
- MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
- Online Meta-Learning
- Unsupervised Data Augmentation for Consistency Training
- A Baseline For Detecting Misclassified and Out-of-Distribution Examples In Neural Networks
- Learning Adversarially Fair and Transferable Representations
- MoCoGAN: Decomposing Motion and Content for Video Generation
- NISP: Pruning Networks using Neural Importance Score Propagation
- -
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- Stand Alone Self Attention in Vision Models
- One ticket to win them all: generalizing lottery ticket initialization
- TSM: Temporal Shift Module for Efficient Video Understanding
- SNIPER:Efficient Multi Scale Training
- Online Model Distillation for Efficient Video Inference
- Bag of Tricks for Image Classification with Convolutional Neural Networks
- Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
- Class-Balanced Loss Based on Effective Number of Samples
- Learning deep representations by mutual information estimation and maximization
- A Closer Look at Few Shot Classification
- PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
- YOLOv3: An Incremental Improvement
- Unsupervised Visual Representation Learning Overview:Toward Self-Supervision
- Zero-Shot Grounding of Objects from Natural Language Queries
- Self-training with Noisy Student improves ImageNet classification
- MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare
- Weight Agnostic Neural Networks
- Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
- FlowNet: Learning Optical Flow with Convolutional Networks
- Quo Vadis, Action Recognition?A New Model and the Kinetics Dataset
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- EfficientDet: Scalable and Efficient Object Detection
- MFAS: Multimodal Fusion Architecture Search
- Hamiltonian Neural Networks
- Learning Correspondence from the Cycle-Consistency of Time
- Adversarial Examples Are Not Bugs, They Are Features
- Revisiting Self-Supervised Visual Representation Learning
- Learning Meta Model for Zero- and Few-shot Face Anti-spoofing
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Discovering Physical Concepts With Neural Networks
- Evidential Deep Learning to Quantify Classification Uncertainty
- Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
- Geonet: Unsupervised learning of dense depth, optical flow and camera pose
- SlowFast Networks for Video Recognition
- Reformer: The Efficient Transformer
- A Simple Framework for Contrastive Learning of Visual Representations
- AutoML-Zero:Evolving Machine Learning Algorithms From Scratch
- Multiplicative Interactions and Where To Find Them
- Zero-Shot Super-Resolution using Deep Internal Learning
- Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models
- HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- Learning in Gated Neural Networks
- Meta Reinforcement Learning as Task Inference
- Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers
- Objects as Points
- -
- Designing Network Design Spaces
- Semantic Pyramid for Image Generation
- A deep learning approach to antibiotics discovery
- A deep learning system for differential diagnosis of skin diseases
- Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
- Temporal Relational Reasoning in Videos
- YOLOv4: Optimal Speed and Accuracy of Object Detection
- Are Transformers universal approximators of sequence-to-sequence functions?
- Reward-Conditioned Policies
- Making Convolutional Networks Shift-Invariant Again
- FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference
- SFNet: Learning Object-aware Semantic Correspondence
- ResNeSt: Split-Attention Networks
- Language Models are Few-Shot Learners
- LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks
- From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
- BERTology meets Biology: Interpreting attention in protein language modeling
- Momentum Contrast for Unsupervised Visual Representation Learning
- Empirical Study of Forgetting Events during Deep Neural Network Learning
- Fast Human Pose Estimation (CVPR 2019)
- MVTec AD-A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
- -
- Probabilistic Model-Agnostic Meta-Learning
- Learning by Analogy: Reliable Supervision From Transformations for Unsupervised O.F.E
- MultiCAM:Multiple class activation mapping for aircraft recognition in remote sensing images
- Adversarial Examples Improve Image Recognition
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images
- PP-YOLO: An Effective and Efficient Implementation of Object Detector
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
- Accelerating Large-Scale Inference with Anisotropic Vector Quantization
- Mixed Precision Training
- On mutual information maximization for representation learning
- On Robustness and Transferability of Convolutional Neural Networks
- Realistic Adversarial Data Augmentation for MR Image Segmentation
- Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
- Robust Benchmarking for Machine Learning of Clinical Entity Extraction
- YOLACT: Real-time Instance Segmentation
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations
- Herring: Rethinking the Parameter Server at Scale for the Cloud
- End-to-End Object Detection with Transformers(DETR)
- Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems
- -
- Quantifying Behaviour of CNNs and Humans by Measuring Error Consistency
- Label Propagation for Deep Semi-supervised Learning
- -
- Do Adversarially Robust ImageNet Models Transfer Better?
- Bridging the Gap Between Anchor-based and Anchor-free Detection via ATSS
- Network Deconvolution
- -
- Document AI - Structured Documents Understanding using Deep Learning
- Dynamic Graph CNN for Learning on Point Clouds
'Routine > 머신러닝' 카테고리의 다른 글
Neural Networks and Deep Learning #Week1 (0) | 2020.02.08 |
---|---|
sparse <-> dense (0) | 2020.02.03 |
ML and deeplearning technology stack (0) | 2020.02.02 |
선형대수학 용어정리 (0) | 2020.02.02 |
Precision & Recall (0) | 2020.02.02 |