AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Residual Calibration via Local Feature-Space Refinement

Xihao Wang, Chengyao Yu, Ruixing Ming

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a post-hoc calibration method that corrects spatially varying miscalibration by refining predictions in local regions of the learned feature space rather than applying a global score-based transformation.

Problem

Deep neural networks give unreliable confidence estimates; existing post-hoc calibration methods are score-based and improve marginal calibration but miss spatially varying miscalibration in local feature-space regions.

Approach

Shifts post-hoc calibration from score-space transformations to local refinement in feature space, estimating calibration adjustments per local region (the abstract is truncated, so the exact estimator is not stated).

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use CFAF-LAPE instead of late fusion for multi-view calibrationmulti-view calibration · Synthetic XOR viewsNLL: 0.507 -> 0.413Improved
Use CFAF-LAPE instead of late fusionmulti-view calibration · Multi-view DigitsNLL: 0.112 -> 0.092Improved
Use CFAF-LAPE instead of late fusionmulti-view calibration · HAM10000 melanoma vs nevusECE: 0.023 -> 0.014Improved
Use CFAF-LAPE instead of late fusionmulti-view calibration · Multi-view Digitsaccuracy: 0.960 -> 0.964No clear effect
Add LAPE residual refinement to TS, VS, FC and SAG anchorspost-hoc calibrators · Obesity Risk, CIFAR-100, BreastMNIST, MHISTNLL and ECEMixed
Use local label frequency from nearest calibration neighbors instead of softmaxprobability estimation · 2D simulation, softmax scores in [0.35,0.65]MAE to oracle probability: 0.156 -> 0.126Improved
Use local frequency alone as a replacement for softmax over all test points (ablation)probability estimation · 100-dim simulation, entire test setMAE to oracle probability: 0.0941 -> 0.1058Hurt
Use local frequency in the predefined boundary region of 100-dim simulationprobability estimation · 100-dim simulation, boundary regionMAE to oracle probability: 0.1067 -> 0.0969Improved
Add more calibration data (ablation)VS+LAPE · calibration-ratio sweepNLLImproved
Use V-fold cross-fitting for anchor scores instead of direct reuse or data splitting (ablation)LAPE · flexible anchors, limited calibration datacalibration qualityImproved

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