Home /
Research
Showing 133 - 138 / 904
Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows
ChengZhang....
Published date-12/01/2020
Variational Bayesian phylogenetic inference (VBPI) provides a promising general variational framework for efficient estimation of phylogenetic posteriors. However, the current diagonal Lognormal branch length approximation would significantly restrict the quality …
Fully Convolutional Networks for Panoptic Segmentation
YanweiLi, HengshuangZhao, XiaojuanQi....
Published date-12/01/2020
PanopticSegmentation
In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff …
Disentangling Label Distribution for Long-tailed Visual Recognition
YoungkyuHong, SeungjuHan, KwangheeChoi....
Published date-12/01/2020
The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol …
Revisiting Parameter Sharing for Automatic Neural Channel Number Search
JiaxingWang, HaoliBai, JiaxiangWu....
Published date-12/01/2020
NeuralArchitectureSearch
Recent advances in neural architecture search inspire many channel number search algorithms~(CNS) for convolutional neural networks. To improve searching efficiency, parameter sharing is widely applied, which reuses parameters among different …
Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds
ValentinLiévin, AndreaDittadi, AndersChristensen....
Published date-12/01/2020
This paper introduces novel results for the score-function gradient estimator of the importance-weighted variational bound (IWAE). We prove that in the limit of large $K$ (number of importance samples) one …
Bidirectional Convolutional Poisson Gamma Dynamical Systems
WenchaoChen, ChaojieWang, BoChen....
Published date-12/01/2020
BayesianInference, VariationalInference
Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but also sentence-level stochastic temporal transitions. …