Reading Notes


(Structured Learning) [2018]
(Image Analsys) [2018]
(Visual Reasoning) [2015]
(Representation Learning) [2018]
(Generative Models) [2017]
(Visual Reasoning) [2019]
(Representation Learning) [2016]

To Read

Adaptive Neural Trees
Analogs of Linguistic Structure in Deep Representations
Categorical Reparametrization with Gumbel-Softmax
Composition and Decomposition of GANs
Convolutional Sequence to Sequence Learning
Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
Deep Learning with Topological Signature
DeepSetNet: Predicting Sets with Deep Neural Networks
Do Neural Networks Show Gestalt Phenomena ?
Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces
Dynamic Routing Between Capsules
Equivariant Transformer Networks
Escaping Plato’s Cave using Adversarial Training: 3D Shape From Unstructured 2D Image Collections
Evaluating ‘Graphical Perception’ with CNNs
GANs for Biological Image Synthesis
Generating Pixel Art from Game Characters with Convolutional-Neural Network
Geometry Score: A Method For Comparing Generative Adversarial Networks
From Machine Learning to Machine Reasoning
Image Transformer
InGAN: Capturing and Remapping the “DNA” of a Natural Image
InfoVAE: Balancing Learning and Inference in Variational Autoencoders
Introspective Classification with Convolutional Nets
Invertible Autoencoder for Domain Adaptation
Learning by Abstraction: The Neural State Machine
Learning Across Tasks and Domains
Learning Inductive Biases with Simple Neural Networks
Learning to describe scenes with programs
Learning to Generate the “Unseen” via Part Synthesis and Composition
Meta-Learning Tutorial
Partial Transfer Learning with Selective Adversarial Networks
Predicting the Future with Transformational States
Reconciling deep learning with symbolic artificial intelligence: representing objects and relations
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
Taming VAEs
The Measure of Intelligence
Time Agnostic Predictions: Predicting Predictable Video Frames
Towards Universal Object Detection by Domain Attention
Unsupervised Discovery of Object Landmarks as Structural Representations
Unsupervised Cipher Cracking using GANs
Unsupervised learning of object landmarks by factorized spatial embeddings
Weakly-supervised Semantic Parsing with Abstract Examples