pith. sign in

arxiv: 2212.05987 · v2 · pith:IQZPZ6VAnew · submitted 2022-12-12 · 💻 cs.LG

Selective classification using a robust meta-learning approach

classification 💻 cs.LG
keywords classificationmeta-objectivepredictiveselectiveuncertaintyaccuracyapplicationsapproach
0
0 comments X
read the original abstract

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%/3.3% accuracy and AUC gains over SOTA in selective classification. We also improve upon large-scale pretrained models such as PLEX.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Exploring the Potential of Bilevel Optimization for Calibrating Neural Networks

    cs.LG 2025-03 unverdicted novelty 5.0

    Bilevel optimization is applied to neural network training to produce self-calibrated confidence scores, reducing calibration error versus isotonic regression on toy and simulated BAC datasets while preserving accuracy.