AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Statistically-motivated Second-order Pooling

Kaicheng Yu, Mathieu Salzmann

ECCV 2018 · Architectures and efficiency › Quantization · approach: Low-precision training formats · 50 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
add parametric vectorization (PV) layer p=2048 in place of full vectorization (ablation)SMSO (VGG-D) · MINC-2500top-1 accuracy: 75.97 -> 75.32No clear effect
add square-root transformation after the PV layer (ablation)SMSO (VGG-D) · MINC-2500top-1 accuracy: 75.32 -> 76.32Improved
add learned scale and bias after the square-root (ablation)SMSO (VGG-D) · MINC-2500top-1 accuracy: 76.32 -> 78.00Improved
add square-root transformation with scale and bias to the PV layer (ablation)SMSO (VGG-D) · MINC-2500top-1 accuracy: 76.14 -> 78.00Improved
use logarithm instead of square-root transformation (ablation)SMSO (VGG-D) · MINC-2500top-1 accuracy: 78.00 -> 77.86No clear effect
use cubic-root instead of square-root transformation (ablation)SMSO (VGG-D) · MINC-2500top-1 accuracy: 78.00 -> 77.17No clear effect
vary PV dimension p from 16 to 8192 (ablation)SMSO (VGG-D) · DTD, MIT, MINCtop-1 accuracyNo clear effect
use SMSO p=2048 instead of plain fine-tuned VGG-DVGG-D · MINC-2500top-1 accuracy: 73.01 -> 78.00Improved
use SMSO p=2048 instead of MPNVGG-D · MINC-2500top-1 accuracy: 76.24 -> 78.00Improved
use SMSO p=2048 instead of plain ResNet-50ResNet-50 · MIT-Indoortop-1 accuracy: 76.45 -> 79.68Improved
use MPN second-order pooling instead of plain ResNet-50ResNet-50 · MIT-Indoortop-1 accuracy: 76.45 -> 72.12Hurt
use learnable PV projection instead of random fixed projection (CBP-TS)SMSO p=2048 (VGG-D) · MINC-2500top-1 accuracy: 73.28 -> 78.00Improved

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