Research map / Label-efficient and robust learning / Test-time adaptation
Learning model uncertainty as variance-minimizing instance weights
Nishant Jain, Karthikeyan Shanmugam, Pradeep Shenoy
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an instance-conditional reweighting method that learns predictive uncertainty via an auxiliary network producing variance-minimizing instance weights, unifying train-time robustness interventions and test-time selective classification.
Problem
Capturing a model's predictive uncertainty (self-awareness of its accuracy on an input) for building robust models via training interventions and for test-time applications such as selective classification.
Approach
An auxiliary network predicts instance-conditional weights that reweight training examples so as to minimize variance, yielding a learned uncertainty estimate usable both during training and at test time.
Closest papers by meaning
- Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks (NeurIPS 2021 · similarity 0.87)
- Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogate (AAAI 2022 · similarity 0.86)
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (NeurIPS 2017 · similarity 0.86)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · similarity 0.86)
- Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models (CVPR 2024 · similarity 0.85)
- From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
