AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction

Alexander Timans, Christoph-Nikolas Straehle, Kaspar Sakmann, Eric Nalisnick

ECCV 2024 · Learning theory and algorithms › Prediction and decision losses · approach: Conformal prediction sets · 14 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
use two-step conformal prediction (class-label ClassThr then box intervals) with alpha_L=0.01, alpha_B=0.1Faster R-CNN on COCO, Cityscapes, BDD100k · COCO, Cityscapes, BDD100klabel and box coverageImproved
use conformal Box-Std intervals instead of deep ensembles or GaussianYOLO uncertaintiesobject detectors · COCO two-sided intervals, target 0.9coverage: 0.21 -> 0.88 (vs DeepEns); 0.08 -> 0.88 (vs GaussianYOLO)Improved
use Box-Std one-sided intervals instead of Andeol et al. bestFaster R-CNN · COCO one-sided intervalsMPIW (pixels): 87.62 -> 85.42Improved
use adaptive Box-Ens or Box-CQR instead of fixed-width Box-Std (ablation)bounding box intervals · BDD100k, coverage stratified by object sizecoverage balance across sizesImproved
use max-rank multiple testing correction instead of Bonferroni (ablation)box coordinate intervals · object detection prediction intervalsinterval widthImproved
use ClassThr label sets instead of the Full label set (ablation)two-step pipeline · COCO, Cityscapes, BDD100kbox interval widthImproved
use Top singleton label set instead of ClassThr (ablation)two-step pipeline · COCO, Cityscapes, BDD100klabel and box coverageHurt
use Naive density-level-set label sets instead of ClassThr (ablation)two-step pipeline · COCO, Cityscapes, BDD100kbox coverageMixed

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