AI Paper Atlas

Research map / Image generation / Image restoration

Beyond IID: Learning to Combine Non-IID Metrics for Vision Tasks

Yinghuan Shi, Wenbin Li, Yang Gao, Longbing Cao, Dinggang Shen

AAAI 2017 · Image generation › Image restoration · approach: Inverse imaging with learned priors · 12 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
replace IID metric learning (LMCA) with non-IID metric learning (NIME-CK)metric learning · MSRC segmentationpixel error rate (%): 5.03 -> 3.27Improved
replace IID metric learning (LMNN) with non-IID metric learning (NIME-CK)metric learning · MSRC segmentationpixel error rate (%): 4.83 -> 3.27Improved
combine three non-IID representations (NIME-CK) instead of the best single one (NIME-MP) (ablation)NIME · MSRC segmentationpixel error rate (%): 3.31 -> 3.27Improved
replace LMNN with NIME-CK non-IID metrichistology image identification · Histology (hand-crafted)accuracy (%): 80.0 -> 89.0Improved
replace LMNN with NIME-CK non-IID metrichistology image identification · Histology (deep features)AUC (%): 86.6 -> 96.9Improved
combine non-IID representations (NIME-CK) instead of single direct-product (NIME-DP) (ablation)NIME · Histology (hand-crafted)accuracy (%): 86.0 -> 89.0Improved
combine non-IID representations (NIME-CK) instead of single NIME-MP (ablation)NIME · Histology (deep features)specificity (%): NIME-DP 89.6 vs NIME-CK 88.5Mixed
switch from hand-crafted to deeply-learned (LeNet) cell featuresNIME-CK · Histology identificationaccuracy (%): 89.0 -> 90.0Improved
vary number of spatial neighbors from 3 to 7 (ablation)NIME · Histology identificationaccuracy: HC: 0.84, 0.89, 0.89, 0.87, 0.87; DL: 0.89, 0.91, 0.90, 0.89, 0.88Mixed

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