Search Results for author:
Found 4 papers, 2 papers with code
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
Equipped with ImageNet-X, we investigate 2, 200 current recognition models and study the types of mistakes as a function of model's (1) architecture, e. g. transformer vs. convolutional, (2) learning paradigm, e. g. supervised vs. self-supervised, and (3) training procedures, e. g., data augmentation.
Simple data balancing achieves competitive worst-group-accuracy
We study the problem of learning classifiers that perform well across (known or unknown) groups of data.
Ranked #1 on
Out-of-Distribution Generalization
on UrbanCars
Masked Adversarial Generation for Neural Machine Translation
Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics.
VirAAL: Virtual Adversarial Active Learning For NLU
The second set shows the effect of VirAAL in an Active Learning (AL) process.
