Research map / Architectures and efficiency / CNN design
Higher-order pooling
Replaces average pooling with kernel, wavelet, stochastic, and bilinear pooling in CNNs.
20 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2024) · an approach in CNN design, keyword cluster “convolution · kernel · spatial”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
2 papers in 2023–24 and 0 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 1.5% to 0.0%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2017 · Low-Rank Bilinear Pooling for Fine-Grained Classification (CVPR 2017 · 381 citations)
- 2018 · Detail-Preserving Pooling in Deep Networks (CVPR 2018 · 150 citations)
- 2019 · Context-Aware Crowd Counting (CVPR 2019 · 765 citations)
- 2020 · Strip Pooling: Rethinking Spatial Pooling for Scene Parsing (CVPR 2020 · 812 citations)
- 2021 · Fast and Compact Bilinear Pooling by Shifted Random Maclaurin (AAAI 2021 · 14 citations)
- 2022 · Efficient Compact Bilinear Pooling via Kronecker Product (AAAI 2022 · 14 citations)
- 2023 · Long Range Pooling for 3D Large-Scale Scene Understanding (CVPR 2023 · 9 citations)
- 2024 · Stacking Deep Set Networks and Pooling by Quantiles (ICML 2024)
Earliest papers here
- Low-Rank Bilinear Pooling for Fine-Grained Classification (CVPR 2017 · 381 citations)
- Kernel Pooling for Convolutional Neural Networks (CVPR 2017 · 378 citations)
- S3Pool: Pooling With Stochastic Spatial Sampling (CVPR 2017 · 84 citations)
What has been tried
19 papers here report 199 measured changes (a component added, removed or swapped, compared with a baseline): helped 69%, no clear effect 6%, hurt 19%, mixed 6%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| combine quantile and average pooling | Sorting clusters · accuracy | 0.7419 ± 0.0034 -> 0.8089 ± 0.0049 | Helped | Stacking Deep Set Networks and Pooling by Quantiles (ICML 2024) |
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 20 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Efficient CNN scaling and dynamic inference (104 papers)
- Dense matching and estimation CNNs (93 papers)
- Invertible and wide-network analysis (65 papers)
- Large and dynamic kernel design (62 papers)
Elsewhere in the topic
- Filter design and trained-filter analysis (128 papers)
- Compact CNN architectures (114 papers)
- Theory of convolutional inductive bias (64 papers)
- Group symmetry equivariant networks (55 papers)
- Biologically inspired CNN explanation (46 papers)
- CNN filter pruning (43 papers)
- Steerable rotation-equivariant CNNs (40 papers)
- Group convolution theory (19 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).