Skip to content

Latest commit

 

History

History
107 lines (95 loc) · 15.3 KB

Papers-2017.md

File metadata and controls

107 lines (95 loc) · 15.3 KB

December 2017

  • Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation - [Arxiv] [QA]
  • Objects that Sound - [Arxiv] [QA]
  • Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks - [Arxiv] [QA]
  • Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions - [Arxiv] [QA]
  • A Probability Monad as the Colimit of Spaces of Finite Samples - [Arxiv] [QA]
  • Geometry-Aware Learning of Maps for Camera Localization - [Arxiv] [QA]
  • Self-supervised Learning of Motion Capture - [Arxiv] [QA]

November 2017

  • Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) - [Arxiv] [QA]
  • Deep Image Prior - [Arxiv] [QA]
  • Backprop as Functor: A compositional perspective on supervised learning - [Arxiv] [QA]
  • Population Based Training of Neural Networks - [Arxiv] [QA]
  • Distilling a Neural Network Into a Soft Decision Tree - [Arxiv] [QA]
  • Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery - [Arxiv] [QA]
  • Contextual-based Image Inpainting: Infer, Match, and Translate - [Arxiv] [QA]
  • Improvements to context based self-supervised learning - [Arxiv] [QA]
  • Dual-Path Convolutional Image-Text Embeddings with Instance Loss - [Arxiv] [QA]
  • Denotational validation of higher-order Bayesian inference - [Arxiv] [QA]
  • Attentional Pooling for Action Recognition - [Arxiv] [QA]
  • Hierarchical Representations for Efficient Architecture Search - [Arxiv] [QA]

October 2017

  • Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks - [Arxiv] [QA]
  • Generalized End-to-End Loss for Speaker Verification - [Arxiv] [QA]
  • Dynamic Routing Between Capsules - [Arxiv] [QA]
  • Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention - [Arxiv] [QA]
  • Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation - [Arxiv] [QA]
  • Searching for Activation Functions - [Arxiv] [QA]
  • Generalization in Deep Learning - [Arxiv] [QA]
  • A systematic study of the class imbalance problem in convolutional neural networks - [Arxiv] [QA]
  • Recent Advances in Zero-shot Recognition - [Arxiv] [QA]
  • Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions - [Arxiv] [QA]

September 2017

  • Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces - [Arxiv] [QA]
  • Information structures and their cohomology - [Arxiv] [QA]
  • N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning - [Arxiv] [QA]
  • AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline - [Arxiv] [QA]
  • ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids - [Arxiv] [QA]

August 2017

  • Disintegration and Bayesian Inversion via String Diagrams - [Arxiv] [QA]
  • Multi-task Self-Supervised Visual Learning - [Arxiv] [QA]
  • Twin Networks: Matching the Future for Sequence Generation - [Arxiv] [QA]
  • Representation Learning by Learning to Count - [Arxiv] [QA]
  • SMASH: One-Shot Model Architecture Search through HyperNetworks - [Arxiv] [QA]
  • Transitive Invariance for Self-supervised Visual Representation Learning - [Arxiv] [QA]
  • PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN - [Arxiv] [QA]
  • Localizing Moments in Video with Natural Language - [Arxiv] [QA]
  • CASSL: Curriculum Accelerated Self-Supervised Learning - [Arxiv] [QA]
  • Unsupervised Representation Learning by Sorting Sequences - [Arxiv] [QA]

July 2017

  • Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering - [Arxiv] [QA]
  • Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback - [Arxiv] [QA]
  • Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly - [Arxiv] [QA]
  • A Channel-Based Perspective on Conjugate Priors - [Arxiv] [QA]

June 2017

  • Bolt: Accelerated Data Mining with Fast Vector Compression - [Arxiv] [QA]
  • Methods for Interpreting and Understanding Deep Neural Networks - [Arxiv] [QA]
  • SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability - [Arxiv] [QA]
  • SmoothGrad: removing noise by adding noise - [Arxiv] [QA]
  • Attention Is All You Need - [Arxiv] [QA]
  • Deep reinforcement learning from human preferences - [Arxiv] [QA]

May 2017

  • Self-supervised learning of visual features through embedding images into text topic spaces - [Arxiv] [QA]
  • Look, Listen and Learn - [Arxiv] [QA]
  • Learning how to explain neural networks: PatternNet and PatternAttribution - [Arxiv] [QA]
  • Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems - [Arxiv] [QA]
  • TALL: Temporal Activity Localization via Language Query - [Arxiv] [QA]
  • Dense-Captioning Events in Videos - [Arxiv] [QA]

April 2017

  • DeepArchitect: Automatically Designing and Training Deep Architectures - [Arxiv] [QA]
  • Unsupervised Learning of Depth and Ego-Motion from Video - [Arxiv] [QA]
  • Detecting and Recognizing Human-Object Interactions - [Arxiv] [QA]
  • Bandit Structured Prediction for Neural Sequence-to-Sequence Learning - [Arxiv] [QA]
  • Equivalence Between Policy Gradients and Soft Q-Learning - [Arxiv] [QA]
  • Learning to Fly by Crashing - [Arxiv] [QA]
  • Unsupervised Learning by Predicting Noise - [Arxiv] [QA]
  • TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering - [Arxiv] [QA]
  • DeepPermNet: Visual Permutation Learning - [Arxiv] [QA]
  • Towards Building Large Scale Multimodal Domain-Aware Conversation Systems - [Arxiv] [QA]

March 2017

  • Tacotron: Towards End-to-End Speech Synthesis - [Arxiv] [QA]
  • Towards Automatic Learning of Procedures from Web Instructional Videos - [Arxiv] [QA]
  • Where to put the Image in an Image Caption Generator - [Arxiv] [QA]
  • Mask R-CNN - [Arxiv] [QA]
  • Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation - [Arxiv] [QA]
  • All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation - [Arxiv] [QA]

February 2017

  • Towards A Rigorous Science of Interpretable Machine Learning - [Arxiv] [QA]
  • Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations - [Arxiv] [QA]
  • Visualizing Deep Neural Network Decisions: Prediction Difference Analysis - [Arxiv] [QA]
  • Face Aging With Conditional Generative Adversarial Networks - [Arxiv] [QA]

January 2017

  • Interactive Learning from Policy-Dependent Human Feedback - [Arxiv] [QA]
  • A Convenient Category for Higher-Order Probability Theory - [Arxiv] [QA]
  • Unsupervised Learning of Long-Term Motion Dynamics for Videos - [Arxiv] [QA]