Selective classification using a robust meta-learning approach
arxiv(2022)
摘要
Predictive uncertainty-a model's self awareness regarding its accuracy on an
input-is key for both building robust models via training interventions and for
test-time applications such as selective classification. We propose a novel
instance-conditioned reweighting approach that captures predictive uncertainty
using an auxiliary network and unifies these train- and test-time applications.
The auxiliary network is trained using a meta-objective in a bilevel
optimization framework. A key contribution of our proposal is the
meta-objective of minimizing the dropout variance, an approximation of Bayesian
Predictive uncertainty. We show in controlled experiments that we effectively
capture the diverse specific notions of uncertainty through this
meta-objective, while previous approaches only capture certain aspects. These
results translate to significant gains in real-world settings-selective
classification, label noise, domain adaptation, calibration-and across
datasets-Imagenet, Cifar100, diabetic retinopathy, Camelyon, WILDs,
Imagenet-C,-A,-R, Clothing1M, etc. For Diabetic Retinopathy, we see upto
3.4
improve upon large-scale pretrained models such as PLEX.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要