AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning to Detect Features in Texture Images

Linguang Zhang, Szymon Rusinkiewicz

CVPR 2018 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 80 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 peakedness-loss tuning to the ranking-trained detector (ablation)Texture-specific feature detector · Carpetrepeatable features: 3290 -> 3715Improved
Add peakedness-loss tuning to the ranking-trained detector (ablation)Texture-specific feature detector · Asphaltrepeatable features: 3332 -> 3344No clear effect
Add peakedness-loss tuning to the ranking-trained detector (ablation)Texture-specific feature detector · Woodrepeatable features: 1892 -> 2906Improved
Add peakedness-loss tuning to the ranking-trained detector (ablation)Texture-specific feature detector · Tilerepeatable features: 3383 -> 3397Mixed
Add peakedness-loss tuning to the ranking-trained detector (ablation)Texture-specific feature detector · Graniterepeatable features: 3384 -> 3431No clear effect
Add peakedness-loss tuning to the ranking-trained detector (ablation)Texture-specific feature detector · Concreterepeatable features: 2716 -> 3607Improved
Add peakedness-loss tuning to the ranking-trained detector (ablation)Texture-specific feature detector · Coarserepeatable features: 3188 -> 3314Improved
Set peakedness-loss weight α above 0.5 (ablation)Tuned detector · Texture imagesrepeatability gainHurt
Use peakedness window w=7 rather than other tested window sizes (ablation)Tuned detector · Texture imagesrepeatability gainImproved
Use k=10 or k=20 scores to compute peakedness (ablation)Tuned detector · Texture imagesrepeatability gainImproved
Train a universal detector on the union of texture images, using ranking loss only (ablation)Feature detector · Cross-texture evaluationrepeatabilityHurt
Train the detector on granite rather than the union of textures (ablation)Feature detector · Cross-texture evaluationrepeatabilityImproved

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