activity
20182022
most citedConfound-leakage: Confound Removal in Machine Learning Leads to Leakage

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

collaborators

9 papers

cs.LG20224 cited

Confound-leakage: Confound Removal in Machine Learning Leads to Leakage

Sami Hamdan, Bradley C. Love, Georg G. von Polier +4

Machine learning (ML) approaches to data analysis are now widely adopted in many fields including epidemiology and medicine. To apply these approaches, confounds must first be remo…

cs.CV2021

Understanding top-down attention using task-oriented ablation design

Freddie Bickford Smith, Brett D Roads, Xiaoliang Luo +1

Top-down attention allows neural networks, both artificial and biological, to focus on the information most relevant for a given task. This is known to enhance performance in visua…

cs.CV2021

A Too-Good-to-be-True Prior to Reduce Shortcut Reliance

Nikolay Dagaev, Brett D. Roads, Xiaoliang Luo +3

Despite their impressive performance in object recognition and other tasks under standard testing conditions, deep networks often fail to generalize to out-of-distribution (o.o.d.)…

cs.CV20201 cited

Enriching ImageNet with Human Similarity Judgments and Psychological Embeddings

Brett D. Roads, Bradley C. Love

Advances in object recognition flourished in part because of the availability of high-quality datasets and associated benchmarks. However, these benchmarks---such as ILSVRC---are r…

cs.LG2020

Robust priors for regularized regression

Sebastian Bobadilla-Suarez, Matt Jones, Bradley C. Love

Induction benefits from useful priors. Penalized regression approaches, like ridge regression, shrink weights toward zero but zero association is usually not a sensible prior. Insp…

cs.CV20201 cited

The perceptual boost of visual attention is task-dependent in naturalistic settings

Freddie Bickford Smith, Xiaoliang Luo, Brett D. Roads +1

Top-down attention allows people to focus on task-relevant visual information. Is the resulting perceptual boost task-dependent in naturalistic settings? We aim to answer this with…