AI Paper Atlas

Research map / Architectures and efficiency / CNN design

From BoW to CNN: Two Decades of Texture Representation for Texture Classification

Li Liu, Jie Chen, Paul Fieguth, Guoying Zhao, Rama Chellappa, Matti Pietikäinen

IJCV 2018 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 408 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
use SVM instead of nearest neighbor classifier with MR8 textonsMR8 texton representation · Texture classification (2440 textons)classification rate: 97.4% -> 98.5%Improved
replace LM/S filter banks with MR8 filterstexton-based classification · texture classificationclassification rateImproved
replace filter bank responses with raw-patch Patch Descriptortexton-based classification · texture classificationclassification rateImproved
use random projection of patches instead of raw Patch DescriptorBoW texture classification · texture classificationclassification rate: 98.5%Improved
use Wavelet-based MFS instead of basic MFSMFS · UIUCclassification rate: 92.3% -> 98.6%Improved
use Wavelet-based MFS instead of basic MFSMFS · UMDclassification rate: 93.9% -> 98.7%Improved
use IFV encoder instead of BoW, LLC or VLAD on CNN featuresCNN texture features · texture datasetsclassification rateImproved
use VGGVD+IFV instead of MRELBPtexture classification · Outex_TC10classification rate: 100% -> 80.0%Hurt
use VGGVD+IFV instead of MRELBPtexture classification · Outex_TC12classification rate: 99.8% -> 82.3%Hurt
pass FVCNN through a neural network to get locally transferred LFVCNNVGGVD+IFV · DTDclassification rate: 72.3% -> 73.8%Improved
pass FVCNN through a neural network to get locally transferred LFVCNNVGGVD+IFV · KTHTIPS2bclassification rate: 81.8% -> 82.6%Improved
pass FVCNN through a neural network to get locally transferred LFVCNNVGGVD+IFV · FMDclassification rate: 79.8% -> 82.1%Improved

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