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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add permutation consistency loss Lpc (ablation) | PCVE · Corel5k (50% missing views, 50% missing labels) | AP: 0.389 -> 0.421 | Improved |
| add permutation consistency loss Lpc (ablation) | PCVE · Pascal07 (50% missing views, 50% missing labels) | AP: 0.547 -> 0.559 | Improved |
| add reconstruction loss Lre (ablation) | PCVE · Corel5k (50% missing views, 50% missing labels) | AP: 0.261 -> 0.421 | Improved |
| add reconstruction loss Lre (ablation) | PCVE · Pascal07 (50% missing views, 50% missing labels) | AP: 0.511 -> 0.559 | Improved |
| add reconstruction loss Lre (ablation) | PCVE · Corel5k (50% missing views, 50% missing labels) | AUC: 0.858 -> 0.913 | Improved |
| add both Lre and Lpc (ablation) | PCVE · Corel5k (50% missing views, 50% missing labels) | AP: 0.350 -> 0.421 | Improved |
| add both Lre and Lpc (ablation) | PCVE · Pascal07 (50% missing views, 50% missing labels) | AP: 0.537 -> 0.559 | Improved |
| use PCVE instead of SIP | PCVE · Pascal07 (50% missing views, 50% missing labels) | AP: 0.555 -> 0.559 | Improved |
| use PCVE instead of MSLPP | PCVE · IAPRTC12 (50% missing views, 50% missing labels) | AP: 0.340 -> 0.336 | Hurt |
| use PCVE instead of SIP | PCVE · MIRFLICKR (50% missing views, 50% missing labels) | AUC: 0.860 -> 0.868 | Improved |
| use iM3C-designed methods (PCVE) instead of non-iM3C methods | PCVE · Pascal07 (50% missing views, 50% missing labels) | AP: 0.508 -> 0.559 | Improved |
| set information-balance beta too small (ablation) | PCVE · Corel5k and Pascal07 | AP | Hurt |
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.
- DICNet — DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification (AAAI 2023) · better on 5 of 5 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
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · similarity 0.93)
- Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification (ICML 2025 · similarity 0.91)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 2024 · similarity 0.90)
- View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning (CVPR 2024 · similarity 0.90)
- Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels (CVPR 2025 · similarity 0.89)
- A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification (AAAI 2024 · similarity 0.89)
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.
