AI Paper Atlas

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

Quality-aware and Soft Consistency Driven Representation Fusion for Incomplete Multi-view Multi-label Classification

Yadong Liu, Waikeung Wong, Yulong Chen, Jie Wen

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Incomplete multi-view multi-label learning · 0 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 soft consistency loss Lsc to backbone (ablation)backbone · Corel5kAP: 0.3406 -> 0.3691Improved
add quality assessment loss Lqa to backbone (ablation)backbone · Corel5kAP: 0.3406 -> 0.4057Improved
add both Lsc and Lqa to backbone (ablation)backbone · Corel5kAP: 0.3406 -> 0.4335Improved
add soft consistency loss Lsc to backbone (ablation)backbone · Pascal07AP: 0.5544 -> 0.5736Improved
add quality assessment loss Lqa to backbone (ablation)backbone · Pascal07AP: 0.5544 -> 0.5708Improved
add both Lsc and Lqa to backbone (ablation)backbone · Pascal07AP: 0.5544 -> 0.5901Improved
add Lsc to model with Lqa (ablation)backbone + Lqa · Corel5kAP: 0.4057 -> 0.4335Improved
add Lqa to model with Lsc (ablation)backbone + Lsc · Pascal07AP: 0.5736 -> 0.5901Improved
learn fusion weights with the quality assessment network instead of direct normalized negative exp-loss (ablation)QUALITY · Corel5KAP: 0.426 -> 0.434Improved
learn fusion weights with the quality assessment network instead of direct normalized negative exp-loss (ablation)QUALITY · Pascal07AP: 0.581 -> 0.590Improved
vary hyper-parameters alpha in [15,30] and beta in [0.5,3.5] (ablation)QUALITY · Pascal07APNo clear effect

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