121 citations · 375 across the 53 of their papers we have counts for
3 papers · 1 filter
Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding
Dominik Filipiak, Andrzej Zapała, Piotr Tempczyk +2
We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation. The proposed architecture relies on the Teacher-Student mutual learn…
On Many-Actions Policy Gradient
Michal Nauman, Marek Cygan
We study the variance of stochastic policy gradients (SPGs) with many action samples per state. We derive a many-actions optimality condition, which determines when many-actions SP…
One Simple Trick to Fix Your Bayesian Neural Network
Piotr Tempczyk, Ksawery Smoczyński, Philip Smolenski-Jensen +1
One of the most popular estimation methods in Bayesian neural networks (BNN) is mean-field variational inference (MFVI). In this work, we show that neural networks with ReLU activa…