Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline

5 Dec 2019vmurahari3/visdial-bert

Prior work in visual dialog has focused on training deep neural models on the VisDial dataset in isolation, which has led to great progress, but is limiting and wasteful.

LANGUAGE MODELLING QUESTION ANSWERING REPRESENTATION LEARNING VISUAL QUESTION ANSWERING

6
05 Dec 2019

Generative Synthesis of Insurance Datasets

5 Dec 2019kasaai/ctgan

One of the impediments in advancing actuarial research and developing open source assets for insurance analytics is the lack of realistic publicly available datasets.

6
05 Dec 2019

The Search for Sparse, Robust Neural Networks

5 Dec 2019justincosentino/robust-sparse-networks

Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts.

NETWORK PRUNING

1
05 Dec 2019

Inter-Level Cooperation in Hierarchical Reinforcement Learning

5 Dec 2019AboudyKreidieh/h-baselines

This article presents a novel algorithm for promoting cooperation between internal actors in a goal-conditioned hierarchical reinforcement learning (HRL) policy.

HIERARCHICAL REINFORCEMENT LEARNING

4
05 Dec 2019

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

5 Dec 2019google-research/augmix

We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.

IMAGE CLASSIFICATION

106
05 Dec 2019

Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space

5 Dec 2019tehqin/EvoStone

Results from experiments with standard continuous optimization benchmarks show that CMA-ME finds better-quality solutions than MAP-Elites; similarly, results on the strategic game Hearthstone show that CMA-ME finds both a higher overall quality and broader diversity of strategies than both CMA-ES and MAP-Elites.

0
05 Dec 2019

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

5 Dec 2019sfzhang15/ATSS

In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them.

OBJECT DETECTION

101
05 Dec 2019

BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

5 Dec 2019Megvii-Nanjing/BBN

Extensive experiments on four benchmark datasets, including the large-scale iNaturalist ones, justify that the proposed BBN can significantly outperform state-of-the-art methods.

REPRESENTATION LEARNING

6
05 Dec 2019

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

5 Dec 2019google/neural-tangents

Neural Tangents is a library designed to enable research into infinite-width neural networks.

BAYESIAN INFERENCE

224
05 Dec 2019

Diversity-Generated Image Inpainting with Style Extraction

4 Dec 2019vivitsai/SEGAN

The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image.

IMAGE INPAINTING

10
04 Dec 2019