AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Is Second-Order Information Helpful for Large-Scale Visual Recognition?

Peihua Li, Jiangtao Xie, Qilong Wang, Wangmeng Zuo

ICCV 2017 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 301 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 first-order max pooling with plain covariance poolingAlexNet · ImageNet 2012 val (1-crop)top-1 error (%): 41.52 -> 40.41Improved
add matrix power normalization (alpha=1/2) to covariance pooling (ablation)AlexNet cov pooling · ImageNet 2012 val (1-crop)top-1 error (%): 40.41 -> 38.51Improved
add M-Fro normalization instead of MPN to covariance pooling (ablation)AlexNet cov pooling · ImageNet 2012 val (1-crop)top-1 error (%): 40.41 -> 39.87Improved
add M-l2 normalization instead of MPN to covariance pooling (ablation)AlexNet cov pooling · ImageNet 2012 val (1-crop)top-1 error (%): 40.41 -> 39.65Improved
combine M-Fro with MPN (ablation)MPN-COV AlexNet · ImageNet 2012 val (1-crop)top-1 error (%): 38.51 -> 39.93Hurt
combine M-l2 with MPN (ablation)MPN-COV AlexNet · ImageNet 2012 val (1-crop)top-1 error (%): 38.51 -> 39.62Hurt
add element-wise power normalization after MPN (ablation)MPN-COV AlexNet · ImageNet 2012 val (1-crop)top-1 error (%): degraded by over 1%Hurt
use warm initialization from max-pooling network instead of random init (ablation)MPN-COV AlexNet · ImageNet 2012 val (1-crop)top-1 error (%): 38.51 -> 37.35Improved
reduce exponent alpha from 1 to about 1/2 (ablation)AlexNet cov pooling · ImageNet 2012 val (1-crop)top-1 error (%): 40.41 -> 38.51Improved
increase alpha above 1 (ablation)AlexNet cov pooling · ImageNet 2012 val (1-crop)top-1 error (%)Hurt
use matrix power normalization instead of matrix logarithm (DeepO2P)second-order pooling AlexNet · ImageNet 2012 val (1-crop)top-1 error (%): 42.16 -> 38.51Improved
use MPN-COV instead of B-CNN element-wise power normalizationsecond-order pooling AlexNet · ImageNet 2012 val (1-crop)top-1 error (%): 39.89 -> 38.51Improved

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