AI Paper Atlas

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

Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval

Zhaopeng Dou, Zhongdao Wang, Weihua Chen, Yali Li, Shengjin Wang

ECCV 2022 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Epistemic versus aleatoric decomposition · 21 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 data uncertainty learning (ablation)UAL (ResNet50) · MSMT17mAP (%): 52.0 -> 53.1Improved
add model uncertainty learning (ablation)UAL (ResNet50) · MSMT17mAP (%): 52.0 -> 52.3Improved
add model uncertainty on top of data uncertainty (ablation)UAL (ResNet50) · MSMT17mAP (%): 53.1 -> 56.5Improved
add data uncertainty learning (ablation)UAL (HRNet-W32) · MSMT17mAP (%): 59.6 -> 62.2Improved
add both uncertainties (ablation)UAL (HRNet-W32) · MSMT17mAP (%): 59.6 -> 65.3Improved
add data uncertainty learning (ablation)BOT(S50) · MSMT17mAP (%): 59.4 -> 59.5No clear effect
add both uncertainties (ablation)BOT(R50) · MSMT17mAP (%): 49.9 -> 53.6Improved
add reliability score weighting of queries (ablation)UAL multi-query · Market-1501 multi-query, Gaussian noisemAP (%): 53.1 -> 71.4Improved
add reliability score weighting of queries (ablation)UAL multi-query · MSMT17 multi-query, motion blurmAP (%): 47.1 -> 54.9Improved
add reliability score weighting of queries (ablation)UAL multi-query · Occluded-REID multi-querymAP (%): 72.2 -> 73.5Improved
increase Bayesian samples T from 10 to 20 (ablation)UAL ResNet50 · CUHK03 labeledmAP (%): 75.6 -> 75.6No clear effect
reduce T from 10 to 5 (ablation)UAL ResNet50 · Market-1501mAP (%): 87.0 -> 86.9No clear effect

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