Latest Research
Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline
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
Generative Synthesis of Insurance Datasets
One of the impediments in advancing actuarial research and developing open source assets for insurance analytics is the lack of realistic publicly available datasets.
The Search for Sparse, Robust Neural 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.
Inter-Level Cooperation in Hierarchical Reinforcement Learning
• AboudyKreidieh/h-baselines
• 
This article presents a novel algorithm for promoting cooperation between internal actors in a goal-conditioned hierarchical reinforcement learning (HRL) policy.
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space
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.
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
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.
BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
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.
Neural Tangents: Fast and Easy Infinite Neural Networks in Python
Neural Tangents is a library designed to enable research into infinite-width neural networks.
Diversity-Generated Image Inpainting with Style Extraction
• vivitsai/SEGAN
•
The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image.