Energy Models for Better Pseudo-Labels: Improving Semi-Supervised
Classification with the 1-Laplacian Graph Energy

Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy

20 June 2019

Angelica I. Aviles-Rivero

Nicolas Papadakis

Samar M. Alsaleh

Carola-Bibiane Schönlieb

Papers citing "Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy"

6 / 6 papers shown

Title
NorMatch: Matching Normalizing Flows with Discriminative Classifiers for Semi-Supervised Learning Zhongying Deng Rihuan Ke Carola-Bibiane Schonlieb Angelica I Aviles-Rivero 17 0 0 17 Nov 2022
LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification P. Sellars Angelica I. Aviles-Rivero Carola-Bibiane Schönlieb 21 8 0 08 Jun 2021
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning Mamshad Nayeem Rizve Kevin Duarte Y. S. Rawat M. Shah 217 508 0 15 Jan 2021
Improved Baselines with Momentum Contrastive Learning Xinlei Chen Haoqi Fan Ross B. Girshick Kaiming He SSL 267 3,369 0 09 Mar 2020
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average Ben Athiwaratkun Marc Finzi Pavel Izmailov A. Wilson 199 243 0 14 Jun 2018
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results Antti Tarvainen Harri Valpola OOD MoMe 261 1,275 0 06 Mar 2017