3 citations · 5 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 2 cited
Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes
Eryk Banatt, Vickram Rajendran, Liam Packer
In practical scenarios, it is often the case that the available training data within the target domain only exist for a limited number of classes, with the remaining classes only a…
cs.LG2019★ 3 cited
Accurate Layerwise Interpretable Competence Estimation
Vickram Rajendran, William LeVine
Estimating machine learning performance 'in the wild' is both an important and unsolved problem. In this paper, we seek to examine, understand, and predict the pointwise competence…