AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

Uddeshya Upadhyay, Shyamgopal Karthik, Yanbei Chen, Massimiliano Mancini, Zeynep Akata

ECCV 2022 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Single-model predictive uncertainty · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add identity mapping loss (ablation)BayesCap · BSD100 super-resolutionUCE: 0.34 -> 0.028Improved
add identity mapping loss (ablation)BayesCap · BSD100 super-resolutionC.Coeff: 0.23 -> 0.45Improved
use BayesCap instead of Generalized Gaussian scratch modelSRGAN · BSD100 super-resolutionUCE: 0.033 -> 0.028Improved
use BayesCap instead of Generalized Gaussian scratch modelSRGAN · BSD100 super-resolutionPSNR: 24.78 -> 25.16Improved
use BayesCap instead of Scratch trained from scratchSRGAN · BSD100 super-resolutionPSNR: 24.39 -> 25.16Improved
use BayesCap instead of post-hoc variance-scaled ScratchSRGAN · BSD100 super-resolutionUCE: 0.036 -> 0.028Improved
use BayesCap instead of ScratchSRGAN · BSD100 super-resolutionECE: 1.26 -> 0.83Improved
use BayesCap instead of dropout (DO)SRGAN · BSD100 super-resolutionNLL: 0.47 -> 0.21Improved

Later papers that compared with this method

1 later accepted paper reports BayesCap as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy