Research map / Label-efficient and robust learning / Recognition and long-tail
Progressive Deep Multi-View Comprehensive Representation Learning
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 PDMF instead of AE2-Nets | Multi-view comprehensive representation learning · Handwritten | accuracy: 96.65±0.32 -> 98.97±0.31 | Helped |
| Use PDMF instead of AE2-Nets | Multi-view comprehensive representation learning · CUB | accuracy: 85.75±0.59 -> 91.26±0.29 | Helped |
| Use PDMF instead of AE2-Nets | Multi-view comprehensive representation learning · Scene15 | accuracy: 67.19±0.42 -> 69.33±0.55 | Helped |
| Use PDMF instead of AE2-Nets | Multi-view comprehensive representation learning · UCIA | accuracy: 80.06±0.39 -> 83.36±0.47 | Helped |
| Remove the auxiliary representation matching term (ablation) | PDMF · Handwritten, CUB, Scene15, and UCIA | accuracy | Hurt |
| Remove the relation-guided scaling-factor term (ablation) | PDMF · Handwritten, CUB, Scene15, and UCIA | accuracy | Hurt |
| Remove all auxiliary-loss terms (ablation) | PDMF · Handwritten, CUB, Scene15, and UCIA | accuracy | Hurt |
| Use the pre-training stage and its auxiliary guidance (ablation) | PDMF · Handwritten, CUB, Scene15, and UCIA | accuracy | Helped |
Closest papers by meaning
- Learning Fused State Representations for Control from Multi-View Observations (ICML 2025 · similarity 0.87)
- Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs (ICLR 2025 · similarity 0.86)
- Rethinking Multi-view Representation Learning via Distilled Disentangling (CVPR 2024 · similarity 0.86)
- SeqMvRL: A Sequential Fusion Framework for Multi-view Representation Learning (CVPR 2025 · similarity 0.86)
- MMRL: Multi-Modal Representation Learning for Vision-Language Models (CVPR 2025 · similarity 0.84)
- DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception (NeurIPS 2024 · similarity 0.84)
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.