activity
20172021
most citedOn Data-Augmentation and Consistency-Based Semi-Supervised Learning

16 citations · 28 across the 7 of their papers we have counts for

collaborators

12 papers

stat.CO2021

Conditional sequential Monte Carlo in high dimensions

Axel Finke, Alexandre H. Thiery

The iterated conditional sequential Monte Carlo (i-CSMC) algorithm from Andrieu, Doucet and Holenstein (2010) is an MCMC approach for efficiently sampling from the joint posterior…

cs.CV2021

Pretrained equivariant features improve unsupervised landmark discovery

Rahul Rahaman, Atin Ghosh, Alexandre H. Thiery

Locating semantically meaningful landmark points is a crucial component of a large number of computer vision pipelines. Because of the small number of available datasets with groun…

stat.ML202116 cited

On Data-Augmentation and Consistency-Based Semi-Supervised Learning

Atin Ghosh, Alexandre H. Thiery

Recently proposed consistency-based Semi-Supervised Learning (SSL) methods such as the -model, temporal ensembling, the mean teacher, or the virtual adversarial training, have a…

eess.IV20204 cited

Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning

Sripad Krishna Devalla, Tan Hung Pham, Satish Kumar Panda +16

Since the introduction of optical coherence tomography (OCT), it has been possible to study the complex 3D morphological changes of the optic nerve head (ONH) tissues that occur al…

eess.IV2019

DeshadowGAN: A Deep Learning Approach to Remove Shadows from Optical Coherence Tomography Images

Haris Cheong, Sripad Krishna Devalla, Tan Hung Pham +9

Purpose: To remove retinal shadows from optical coherence tomography (OCT) images of the optic nerve head(ONH). Methods:2328 OCT images acquired through the center of the ONH using…

stat.ME2019

Sequential Ensemble Transform for Bayesian Inverse Problems

Aaron Myers, Alexandre H. Thiery, Kainan Wang +1

We present the Sequential Ensemble Transform (SET) method, an approach for generating approximate samples from a Bayesian posterior distribution. The method explores the posterior…