Research map / Learning theory and algorithms / Optimal transport
Regularized Optimal Transport Layers for Generalized Global Pooling Operations
Hongteng Xu, Minjie Cheng
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 |
|---|---|---|---|
| replace mean pooling with ROTP_S | AttentionDeepMIL · MIL Messidor | accuracy (%): 74.42 -> 75.42 | Improved |
| replace gated attention pooling with ROTP_S | AttentionDeepMIL · MIL Function | accuracy (%): 96.51 -> 96.62 | Improved |
| replace Mixed pooling with ROTP_S | AttentionDeepMIL · MIL Component | accuracy (%): 93.45 -> 93.29 | No clear effect |
| replace OTK with ROTP_S | AttentionDeepMIL · MIL Messidor | accuracy (%): 74.78 -> 75.42 | Improved |
| add learnable alpha0 to ROTP_B-E (ablation) | ROTP_B-E · MIL Messidor | accuracy (%): 74.83 -> 75.33 | Improved |
| add learnable alpha0 to ROTP_B-Q (ablation) | ROTP_B-Q · MIL Messidor | accuracy (%): 75.08 -> 75.17 | No clear effect |
| add learnable alpha0 to ROTP_B-Q (ablation) | ROTP_B-Q · MIL Component | accuracy (%): 93.13 -> 93.45 | Improved |
| add learnable alpha0 to ROTP_B-E (ablation) | ROTP_B-E · MIL Component | accuracy (%): 93.16 -> 93.16 | No clear effect |
| add learnable alpha0 to ROTP_B-Q (ablation) | ROTP_B-Q · MIL Function | accuracy (%): 96.09 -> 96.22 | Improved |
| add learnable alpha0 to ROTP_B-E (ablation) | ROTP_B-E · MIL Function | accuracy (%): 96.17 -> 96.22 | No clear effect |
Closest papers by meaning
- Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree (TPAMI 2017 · similarity 0.88)
- Towards a Deeper Understanding of Global Covariance Pooling in Deep Learning: An Optimization Perspective (TPAMI 2023 · similarity 0.86)
- Rethinking pooling in graph neural networks (NeurIPS 2020 · similarity 0.86)
- Global Feature Guided Local Pooling (ICCV 2019 · similarity 0.86)
- Geometry-Aware Edge Pooling for Graph Neural Networks (NeurIPS 2025 · similarity 0.86)
- SkipPool: Improved Sparse Hierarchical Graph Pooling with Differentiable Exploration (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.
