Research map / Label-efficient and robust learning / Recognition and long-tail
Versatile Multiple Choice Learning and Its Application to Vision Computing
Check 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 vMCL instead of CMCL | 3-conv-layer ensemble · CIFAR-10 | Top-1 error: 13.82% -> 12.03% | Helped |
| Use vMCL instead of sMCL | 3-conv-layer ensemble · CIFAR-10 | Oracle error: 2.43% -> 1.37% | Helped |
| Use vMCL instead of IE | 3-conv-layer ensemble · SVHN | Top-1 error: 5.64% -> 5.88% | Hurt |
| Use vMCL instead of CMCL | 3-conv-layer ensemble · SVHN | Oracle error: 1.62% -> 1.22% | Helped |
| Use vMCL instead of CMCL | 3-conv-layer ensemble · CIFAR-100 | Top-1 error: 41.25% -> 38.07% | Helped |
| Use vMCL instead of CMCL | FCN ensemble · iCoseg | Oracle error: 7.8% -> 3.07% | Helped |
| Add shared layers (ablation) | vMCL · CIFAR-10 | Top-1 error: 15.14% -> 13.74% | Helped |
| Add shared layers (ablation) | vMCL · CIFAR-10 | Oracle error: 1.79% -> 1.55% | Helped |
| Add choice network (ablation) | vMCL · CIFAR-10 | Top-1 error: 15.14% -> 13.64% | Helped |
| Add choice network (ablation) | vMCL · CIFAR-10 | Oracle error: 1.79% -> 1.14% | Helped |
| Add both shared layers and choice network (ablation) | vMCL · CIFAR-10 | Top-1 error: 15.14% -> 12.03% | Helped |
| Add both shared layers and choice network (ablation) | vMCL · CIFAR-10 | Oracle error: 1.79% -> 1.37% | Helped |
Closest papers by meaning
- Vision-Language Model Selection and Reuse for Downstream Adaptation (ICML 2025 · similarity 0.83)
- Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing (NeurIPS 2024 · similarity 0.83)
- Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training (ICML 2025 · similarity 0.82)
- Multiple Hypothesis Dropout: Estimating the Parameters of Multi-Modal Output Distributions (AAAI 2024 · similarity 0.82)
- Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models (ICML 2024 · similarity 0.82)
- Confidence-aware Contrastive Learning for Selective Classification (ICML 2024 · similarity 0.82)
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.