Research map / Detection and segmentation / CNN features
LiftPool: Bidirectional ConvNet Pooling
Jiaojiao Zhao, Cees G. M. Snoek
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 MaxPool with LiftDownPool | ResNet50 · ImageNet | error rate: 1.9% | Improved |
| Increase LiftPool kernel size from 5 to 7 (ablation) | VGG13 · CIFAR100 | top-1 error: 24.35% -> 24.40% | No clear effect |
Closest papers by meaning
- Refining Activation Downsampling With SoftPool (ICCV 2021 · similarity 0.88)
- S3Pool: Pooling With Stochastic Spatial Sampling (CVPR 2017 · similarity 0.87)
- Detail-Preserving Pooling in Deep Networks (CVPR 2018 · similarity 0.87)
- TI-Pooling: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks (CVPR 2016 · similarity 0.87)
- Beyond Skip Connection: Pooling and Unpooling Design for Elimination Singularities (AAAI 2025 · similarity 0.86)
- Geometry-Aware Edge Pooling for Graph Neural Networks (NeurIPS 2025 · similarity 0.83)
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.
