Research map / Label-efficient and robust learning / Recognition and long-tail
DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use DICNet instead of NAIML | DIMVMLC classification · Corel 5k | AP: 0.309$\pm$0.004 -> 0.381$\pm$0.004 | Helped |
| Use DICNet instead of NAIML | DIMVMLC classification · VOC 2007 | AP: 0.488$\pm$0.003 -> 0.505$\pm$0.012 | Helped |
| Use DICNet instead of NAIML | DIMVMLC classification · ESP Game | AP: 0.246$\pm$0.002 -> 0.297$\pm$0.002 | Helped |
| Use DICNet instead of NAIML | DIMVMLC classification · IAPR TC-12 | AP: 0.261$\pm$0.001 -> 0.323$\pm$0.001 | Helped |
| Use DICNet instead of NAIML | DIMVMLC classification · MIR FLICKR | AP: 0.551$\pm$0.002 -> 0.589$\pm$0.005 | Helped |
| Add feature reconstruction loss (ablation) | DICNet with MC loss only · Corel5k | AP: 0.336 -> 0.352 | Helped |
| Add feature reconstruction loss (ablation) | DICNet with MC loss only · VOC2007 | AP: 0.484 -> 0.492 | Helped |
| Add instance-level contrastive loss (ablation) | DICNet with MC loss only · Corel5k | AP: 0.336 -> 0.368 | Helped |
| Add instance-level contrastive loss (ablation) | DICNet with MC loss only · VOC2007 | AP: 0.484 -> 0.504 | Helped |
| Add instance-level contrastive loss to MC + FR (ablation) | DICNet · Corel5k | AP: 0.352 -> 0.381 | Helped |
| Add instance-level contrastive loss to MC + FR (ablation) | DICNet · VOC2007 | AP: 0.492 -> 0.505 | Helped |
| Add feature reconstruction loss to MC + IC (ablation) | DICNet · Corel5k | AP: 0.368 -> 0.381 | Helped |
Closest papers by meaning
- Deep Incomplete Multi-View Learning Network with Insufficient Label Information (AAAI 2024 · similarity 0.90)
- Learning Compact Semantic Information for Incomplete Multi-View Missing Multi-Label Classification (ICML 2025 · similarity 0.90)
- CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning (AAAI 2025 · similarity 0.90)
- Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels (CVPR 2025 · similarity 0.90)
- Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification (AAAI 2024 · similarity 0.89)
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · 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.