activity
20192022
most citedTest-time Fourier Style Calibration for Domain Generalization

4 citations · 9 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CL20221 cited

LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue

Anthony Sicilia, Malihe Alikhani

Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lex…

cs.CV20224 cited

Test-time Fourier Style Calibration for Domain Generalization

Xingchen Zhao, Chang Liu, Anthony Sicilia +2

The topic of generalizing machine learning models learned on a collection of source domains to unknown target domains is challenging. While many domain generalization (DG) methods…

cs.CL2022

The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error

Katherine Atwell, Anthony Sicilia, Seong Jae Hwang +1

Discourse analysis allows us to attain inferences of a text document that extend beyond the sentence-level. The current performance of discourse models is very low on texts outside…

cs.LG2021

PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging

Anthony Sicilia, Xingchen Zhao, Anastasia Sosnovskikh +1

Application of deep neural networks to medical imaging tasks has in some sense become commonplace. Still, a "thorn in the side" of the deep learning movement is the argument that d…

cs.CV2021

Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning

Anthony Sicilia, Xingchen Zhao, Davneet Minhas +5

We consider a model-agnostic solution to the problem of Multi-Domain Learning (MDL) for multi-modal applications. Many existing MDL techniques are model-dependent solutions which e…

cs.CV20211 cited

Robust White Matter Hyperintensity Segmentation on Unseen Domain

Xingchen Zhao, Anthony Sicilia, Davneet Minhas +5

Typical machine learning frameworks heavily rely on an underlying assumption that training and test data follow the same distribution. In medical imaging which increasingly begun a…