AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Recognizing Material Properties from Images

Gabriel Schwartz, Ko Nishino

TPAMI 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Human perception modeling

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 more discovered attributes beyond M=30 (ablation)Discovered attributes + SVM · FMDaccuracy: less than 0.1% gain past M=30No clear effect
remove attribute layers from MAC-CNN (ablation)MAC-CNN · Material databaseaverage material category accuracyNo clear effect
constrain a top layer before softmax to output previously discovered attributesMaterial recognition CNN · Attribute predictionmean average error: 0.2 vs 0.08Hurt
add attribute constraint layer before softmaxMaterial recognition CNN · Material databasematerial accuracyNo clear effect
increase training set size for attribute discovery (ablation)Discovered attributes · FMDaccuracyNo clear effect
add attribute probabilities to material probabilities as features (ablation)Novel category linear SVM · Held-out material categoriesnovel category recognition accuracyImproved
use local patches only instead of contextMaterial recognition · FMDaccuracy: 57.1% to 42.6%Hurt

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