Research map / Architectures and efficiency / CNN design
Kernel Pooling for Convolutional Neural Networks
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 learned Kernel Pooling instead of Compact Bilinear Pooling | VGG-16 · CUB-200-2011 | accuracy: 84.3 -> 86.2 | Helped |
| Use learned Kernel Pooling instead of Compact Bilinear Pooling | ResNet-50 · CUB-200-2011 | accuracy: 81.6 -> 84.7 | Helped |
| Use learned Kernel Pooling instead of Compact Bilinear Pooling | VGG-16 · Stanford Cars | accuracy: 91.2 -> 92.6 | Helped |
| Use learned Kernel Pooling instead of Compact Bilinear Pooling | ResNet-50 · Stanford Cars | accuracy: 88.6 -> 91.1 | Helped |
| Use learned Kernel Pooling instead of Compact Bilinear Pooling | VGG-16 · Aircraft | accuracy: 84.1 -> 86.9 | Helped |
| Use learned Kernel Pooling instead of Compact Bilinear Pooling | ResNet-50 · Aircraft | accuracy: 81.6 -> 85.7 | Helped |
| Use learned Kernel Pooling instead of Compact Bilinear Pooling | VGG-16 · Food-101 | accuracy: 82.4 -> 84.2 | Helped |
| Use learned Kernel Pooling instead of Compact Bilinear Pooling | ResNet-50 · Food-101 | accuracy: 83.2 -> 85.5 | Helped |
Closest papers by meaning
- Learning with convolution and pooling operations in kernel methods (NeurIPS 2022 · similarity 0.91)
- Approximation and Learning with Deep Convolutional Models: a Kernel Perspective (ICLR 2022 · similarity 0.90)
- End-to-End Kernel Learning with Supervised Convolutional Kernel Networks (NeurIPS 2016 · similarity 0.89)
- Compact Bilinear Pooling (CVPR 2016 · similarity 0.88)
- Kernelized Subspace Pooling for Deep Local Descriptors (CVPR 2018 · similarity 0.87)
- Gaussian-Based Pooling for Convolutional Neural Networks (NeurIPS 2019 · similarity 0.87)
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.