NeurIPS 2016

Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision

NeurIPS 2016 tensorflow/models

We demonstrate the ability of the model in generating 3D volume from a single 2D image with three sets of experiments: (1) learning from single-class objects; (2) learning from multi-class objects and (3) testing on novel object classes.

3D OBJECT RECONSTRUCTION

Unsupervised Learning for Physical Interaction through Video Prediction

NeurIPS 2016 tensorflow/models

A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment.

VIDEO PREDICTION

Can Active Memory Replace Attention?

NeurIPS 2016 tensorflow/models

Several mechanisms to focus attention of a neural network on selected parts of its input or memory have been used successfully in deep learning models in recent years.

IMAGE CAPTIONING MACHINE TRANSLATION

Domain Separation Networks

NeurIPS 2016 tensorflow/models

However, by focusing only on creating a mapping or shared representation between the two domains, they ignore the individual characteristics of each domain.

UNSUPERVISED DOMAIN ADAPTATION

Deep Exploration via Bootstrapped DQN

NeurIPS 2016 tensorflow/models

Efficient exploration in complex environments remains a major challenge for reinforcement learning.

ATARI GAMES EFFICIENT EXPLORATION

Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks

NeurIPS 2016 tensorflow/models

We study the problem of synthesizing a number of likely future frames from a single input image.

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

NeurIPS 2016 tensorflow/models

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.

IMAGE GENERATION REPRESENTATION LEARNING UNSUPERVISED IMAGE CLASSIFICATION UNSUPERVISED MNIST

Improved Techniques for Training GANs

NeurIPS 2016 tensorflow/models

We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework.

CONDITIONAL IMAGE GENERATION SEMI-SUPERVISED IMAGE CLASSIFICATION

R-FCN: Object Detection via Region-based Fully Convolutional Networks

NeurIPS 2016 facebookresearch/detectron

In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.

REAL-TIME OBJECT DETECTION

Coupled Generative Adversarial Networks

NeurIPS 2016 eriklindernoren/Keras-GAN

We propose coupled generative adversarial network (CoGAN) for learning a joint distribution of multi-domain images.

DOMAIN ADAPTATION IMAGE-TO-IMAGE TRANSLATION