AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Thread Counting in Plain Weave for Old Paintings Using Regression Deep Learning Models

Antonio Delgado, Juan José Murillo-Fuentes, Laura Alba Carcelén

IJCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 0 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 segmentation with direct regression (Reg-VGG)Inc-Dice thread counting · test setNMAE (%): 1.51 -> 1.02Improved
replace segmentation with direct regression (Reg-VGG)Inc-Dice thread counting · validation setNMAE (%): 1.12 -> 0.92Improved
add preprocessing improvements (equalization, variable window, crops, limited rotation) to segmentationInc-Dice · validation setNMAE (%): 1.12 -> 1.04Improved
add the dataset-generation improvementsInc-Dice · test setNMAE (%): 1.61 -> 1.51Improved
reuse pre-trained segmentation encoder instead of training from scratchregression model · validation setNMAE (%)Hurt
add residual connections to inception regressionReg · validation setNMAE (%)No clear effect
use VGG-style layout instead of plain inception regressionReg · validation setNMAE (%): 0.92Improved
add histogram equalization to preprocessing (ablation)Reg-VGG · test setNMAEImproved
add variable-size filtering window instead of fixed window (ablation)Reg-VGG · test setNMAEImproved
add central patches from labeled samples to data augmentation (ablation)Reg-VGG · test setNMAEImproved
limit maximum random rotation angle in augmentation (ablation)Reg-VGG · test setNMAEImproved
add semi-supervised refinement using FT agreementReg-VGG · test setNMAE (%): 1.01 -> 0.94Improved

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