Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Robust Representations via Multi-View Information Bottleneck
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 MIB instead of MV-InfoMax | Sketchy sketch-based image retrieval · Sketchy | mAP@all: 0.008 -> 0.856±0.005 | Helped |
| Use MIB instead of MV-InfoMax | Sketchy sketch-based image retrieval · Sketchy | Prec@200: 0.008 -> 0.848±0.005 | Helped |
| Use a 64-bits binary representation (ablation) | MIB · Sketchy | mAP@all: 0.856±0.005 -> 0.851± 0.004 | Hurt |
| Use a 64-bits binary representation (ablation) | MIB · Sketchy | Prec@200: 0.848±0.005 -> 0.834±0.003 | Hurt |
| Increase the compression strength β (ablation) | MIB on MIR-Flickr · MIR-Flickr, scarce-label regimes | mAP | Helped |
| Increase the compression strength β (ablation) | MIB on MIR-Flickr · MIR-Flickr, all labels | mAP | Hurt |
| Use MIB with β=1 | Single-view MNIST representation learning · MNIST, scarce-label evaluation | classification accuracy | Helped |
Closest papers by meaning
- Rethinking Multi-view Representation Learning via Distilled Disentangling (CVPR 2024 · similarity 0.88)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 2024 · similarity 0.87)
- Structured IB: Improving Information Bottleneck with Structured Feature Learning (AAAI 2025 · similarity 0.86)
- Multi-View Causal Representation Learning with Partial Observability (ICLR 2024 · similarity 0.86)
- Differentiable Information Bottleneck for Deterministic Multi-view Clustering (CVPR 2024 · similarity 0.85)
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · similarity 0.85)
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.