Research map / Label-efficient and robust learning / Recognition and long-tail
Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation
Xu Yan, Jun Yin, Shiliang Sun, Minghua Wan
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 fused-teacher self-distillation loss (ablation) | SCSD · Corel5k | AP: 0.376 -> 0.447 | Improved |
| add fused-teacher self-distillation loss (ablation) | SCSD · Pascal07 | AP: 0.560 -> 0.578 | Improved |
| add KL imitation term of self-distillation (ablation) | SCSD · Corel5k | AP: 0.411 -> 0.447 | Improved |
| add reconstruction loss (ablation) | SCSD · Corel5k | AP: 0.439 -> 0.447 | Improved |
| add vector quantization with shared codebook (ablation) | SCSD · Corel5k | AP: 0.430 -> 0.447 | Improved |
| add vector quantization with shared codebook (ablation) | SCSD · Pascal07 | AP: 0.565 -> 0.578 | Improved |
| add cross-view reconstruction (ablation) | SCSD · Pascal07 | AP: 0.553 -> 0.578 | Improved |
| use label-correlation weighted fusion instead of masked average (ablation) | SCSD · Corel5k | AP: 0.445 -> 0.447 | Improved |
| use label-correlation weighted fusion instead of masked average (ablation) | SCSD · Pascal07 | AP: 0.570 -> 0.578 | Improved |
| vary temperature tau in fusion (ablation) | SCSD · Corel5k and Pascal07 | AP | No 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.
- DICNet — DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification (AAAI 2023) · better on 1 of 1 shared result
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
- Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification (ICML 2025 · similarity 0.93)
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · similarity 0.92)
- View-Category Interactive Sharing Transformer for Incomplete Multi-View Multi-Label Learning (CVPR 2024 · similarity 0.91)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 2024 · similarity 0.91)
- A Two-Stage Information Extraction Network for Incomplete Multi-View Multi-Label Classification (AAAI 2024 · similarity 0.90)
- CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · similarity 0.90)
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.
