Research map / Label-efficient and robust learning / Self-supervised and contrastive
Multiview Self-Representation Learning across Heterogeneous Views
Jie Chen, Zhu Wang, Chuanbin Liu, Xi Peng
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 cross-view assignment consistency loss Lc (ablation) | MSRL · GTSRB clustering | ACC: 40.00 -> 49.78 | Improved |
| add cross-view assignment consistency loss Lc (ablation) | MSRL · CIFAR-100 clustering | ACC: 84.82 -> 91.00 | Improved |
| add cross-view assignment consistency loss Lc (ablation) | MSRL · ImageNet-1K clustering | ACC: 72.31 -> 73.24 | Improved |
| use attention-based feature aggregation (FSRL) instead of identity matrix (ablation) | MSRL · GTSRB clustering | ACC: 42.63 -> 49.78 | Improved |
| use attention-based feature aggregation (FSRL) instead of identity matrix (ablation) | MSRL · Aircraft clustering | ARI: 27.79 -> 27.72 | No clear effect |
| use attention-based feature aggregation (FSRL) instead of identity matrix (ablation) | MSRL · ImageNet-1K clustering | ACC: 71.93 -> 73.24 | Improved |
| add a lower-quality pretrained view (ViT-B/32) to the model set (ablation) | MSRL · eight vision datasets | clustering performance | Hurt |
| increase number of pretrained views to all four models (ablation) | MSRL · eight vision datasets | clustering performance | No clear effect |
| vary training batch size (ablation) | MSRL · GTSRB and CIFAR-100 clustering | ACC, NMI, ARI | No clear effect |
| compare MSRL against CLIP zero-shot transfer and LaFTer using class descriptions | MSRL · GTSRB and ImageNet-1K | ACC | Hurt |
Closest papers by meaning
- Towards Efficient and Effective Self-Supervised Learning of Visual Representations (ECCV 2022 · similarity 0.88)
- Exploit Clues From Views: Self-Supervised and Regularized Learning for Multiview Object Recognition (CVPR 2020 · similarity 0.88)
- Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs (ICLR 2025 · similarity 0.87)
- Rethinking Multi-view Representation Learning via Distilled Disentangling (CVPR 2024 · similarity 0.87)
- Self-Organizing Visual Prototypes for Non-Parametric Representation Learning (ICML 2025 · similarity 0.86)
- Can Generative Models Improve Self-Supervised Representation Learning? (AAAI 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.
