NeurIPS 2018

Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning

NeurIPS 2018 tensorflow/models

We demonstrate this framework on 3D pose estimation by proposing a differentiable objective that seeks the optimal set of keypoints for recovering the relative pose between two views of an object.


SNIPER: Efficient Multi-Scale Training

NeurIPS 2018 MahyarNajibi/SNIPER

Our implementation based on Faster-RCNN with a ResNet-101 backbone obtains an mAP of 47.6% on the COCO dataset for bounding box detection and can process 5 images per second during inference with a single GPU.


Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents

NeurIPS 2018 uber-common/deep-neuroevolution

Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep neural networks roughly as well as Q-learning and policy gradient methods on challenging deep reinforcement learning (RL) problems, but are much faster (e.g. hours vs. days) because they parallelize better.


GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration

NeurIPS 2018 cornellius-gp/gpytorch

Despite advances in scalable models, the inference tools used for Gaussian processes (GPs) have yet to fully capitalize on developments in computing hardware.

PointCNN: Convolution On X-Transformed Points

NeurIPS 2018 yangyanli/PointCNN

We present a simple and general framework for feature learning from point cloud.

Visual Reinforcement Learning with Imagined Goals

NeurIPS 2018 vitchyr/rlkit

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires.


Are GANs Created Equal? A Large-Scale Study

NeurIPS 2018 google/compare_gan

Generative adversarial networks (GAN) are a powerful subclass of generative models.

FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network

NeurIPS 2018 Microsoft/EdgeML

FastRNN addresses these limitations by adding a residual connection that does not constrain the range of the singular values explicitly and has only two extra scalar parameters.

FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction

NeurIPS 2018 kevin-ssy/FishNet

The basic principles in designing convolutional neural network (CNN) structures for predicting objects on different levels, e.g., image-level, region-level, and pixel-level are diverging.


Learning Disentangled Joint Continuous and Discrete Representations

NeurIPS 2018 Schlumberger/joint-vae

We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner.