Research map / Label-efficient and robust learning / Recognition and long-tail
Masked Two-channel Decoupling Framework for Incomplete Multi-view Weak Multi-label Learning
Chengliang Liu, Jie Wen, Yabo Liu, Chao Huang, Zhihao Wu, Xiaoling Luo, Yong Xu
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 random fragment masking of input features (ablation) | MTD · Corel5k | AP: 0.397 -> 0.415 | Improved |
| add random fragment masking (ablation) | single-channel baseline · Corel5k | AP: 0.372 -> 0.396 | Improved |
| add random fragment masking (ablation) | two-channel baseline · Corel5k | AP: 0.387 -> 0.408 | Improved |
| decouple single channel into shared and view-private channels (ablation) | baseline · Corel5k | AP: 0.396 -> 0.408 | Improved |
| add weak label-guided graph regularization (ablation) | two-channel baseline · Corel5k | AP: 0.408 -> 0.409 | No clear effect |
| add weak label-guided graph regularization (ablation) | two-channel baseline · Corel5k | 1-OE: 0.482 -> 0.488 | Improved |
| add reconstruction loss (ablation) | d_ch+L_gc · Corel5k | AP: 0.409 -> 0.413 | Improved |
| add cross-channel contrastive loss (ablation) | d_ch+L_re+L_gc · Corel5k | AP: 0.413 -> 0.415 | Improved |
| MTD vs DICNet on IAPRTC12 1-OE | MTD · IAPRTC12 | 1-OE: 0.468 -> 0.467 | Hurt |
| mask rate varied (too large or too small) (ablation) | MTD · Corel5k/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 9 of 9 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 0.88)
- Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels (CVPR 2025 · similarity 0.88)
- Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification (AAAI 2024 · similarity 0.87)
- Double-Layer Hybrid-Label Identification Feature Selection for Multi-View Multi-Label Learning (AAAI 2024 · similarity 0.87)
- Deep Incomplete Multi-View Learning Network with Insufficient Label Information (AAAI 2024 · similarity 0.87)
- Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification (ICML 2025 · similarity 0.86)
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.
