AI Paper Atlas

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

Permutation-Consistent Variational Encoding for Incomplete Multi-View Multi-Label Classification

Chengliang Liu, Bo Li, Bob Zhang, Xiaoling Luo, Yabo Liu, Jie Wen

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Incomplete multi-view multi-label learning

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 permutation consistency loss Lpc (ablation)PCVE · Corel5k (50% missing views, 50% missing labels)AP: 0.389 -> 0.421Improved
add permutation consistency loss Lpc (ablation)PCVE · Pascal07 (50% missing views, 50% missing labels)AP: 0.547 -> 0.559Improved
add reconstruction loss Lre (ablation)PCVE · Corel5k (50% missing views, 50% missing labels)AP: 0.261 -> 0.421Improved
add reconstruction loss Lre (ablation)PCVE · Pascal07 (50% missing views, 50% missing labels)AP: 0.511 -> 0.559Improved
add reconstruction loss Lre (ablation)PCVE · Corel5k (50% missing views, 50% missing labels)AUC: 0.858 -> 0.913Improved
add both Lre and Lpc (ablation)PCVE · Corel5k (50% missing views, 50% missing labels)AP: 0.350 -> 0.421Improved
add both Lre and Lpc (ablation)PCVE · Pascal07 (50% missing views, 50% missing labels)AP: 0.537 -> 0.559Improved
use PCVE instead of SIPPCVE · Pascal07 (50% missing views, 50% missing labels)AP: 0.555 -> 0.559Improved
use PCVE instead of MSLPPPCVE · IAPRTC12 (50% missing views, 50% missing labels)AP: 0.340 -> 0.336Hurt
use PCVE instead of SIPPCVE · MIRFLICKR (50% missing views, 50% missing labels)AUC: 0.860 -> 0.868Improved
use iM3C-designed methods (PCVE) instead of non-iM3C methodsPCVE · Pascal07 (50% missing views, 50% missing labels)AP: 0.508 -> 0.559Improved
set information-balance beta too small (ablation)PCVE · Corel5k and Pascal07APHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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