AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Generalizing Pooling Functions in CNNs: Mixed, Gated, and Tree

Chen‐Yu Lee, Patrick Gallagher, Zhuowen Tu

TPAMI 2017 · Architectures and efficiency › CNN design · approach: Higher-order pooling · 560 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace max pooling with gated max-avg pooling (1 per layer)DSN-style CNN · CIFAR10test error (%): 9.10 -> 7.90Improved
make the max-avg mix responsive via a gate rather than a fixed learned mixmixed max-avg pooling · CIFAR10test error (%): 8.09 -> 7.90Improved
increase mixed parameters from 1 per layer to 1 per layer/channel/region (ablation)mixed max-avg pooling · CIFAR10test error (%): 8.09 -> 8.05No clear effect
use per layer/channel/region mixing on large data (ablation)mixed max-avg pooling · SVHNtest error (%): 1.76 -> 1.64Improved
add learning of the mix proportion versus fixed 50/50 (ablation)max-avg pooling · CIFAR10test error (%): 8.11 -> 7.90Improved
add a second tree level (ablation)tree pooling · CIFAR10test error (%): 8.25 -> 8.22No clear effect
add a third tree level (ablation)tree pooling · SVHNtest error (%): 1.80 -> 1.70Improved
add a third tree level (ablation)tree pooling · MNISTtest error (%): 0.35 -> 0.37Hurt
follow tree pooling with gated max-avg in second pooling layer (ablation)tree pooling · CIFAR10test error (%): 8.22 -> 7.62Improved
add two extra conv layers instead of learned pooling (ablation)baseline CNN · CIFAR10test error (%): 9.10 -> 9.17Hurt
add one extra conv layer instead of learned pooling (ablation)baseline CNN · CIFAR10test error (%): 9.10 -> 9.08No clear effect
replace max pooling with stochastic pooling (ablation)baseline CNN · CIFAR10test error (%): 9.10 -> 8.50Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy