AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning

Nan Xue, Tianfu Wu, Song Bai, Fudong Wang, Gui-Song Xia, Liangpei Zhang, Philip H. S. Torr

TPAMI 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 64 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
upgrade HAWPv1 to HAWPv2HAWP · WireframesAP5: 62.5 -> 65.7Improved
upgrade HAWPv1 to HAWPv2HAWP · YorkUrbansAP5: 26.1 -> 28.8Improved
upgrade HAWPv1 to HAWPv2HAWP · WireframeFPS: 29.5 -> 40.8Improved
add end-point decoupled feature aggregation (ablation)LOIAlign · WireframesAP5: 64.0 -> 65.3Improved
add features of intermediate points on proposed line segments (ablation)EPD LOIAlign · WireframesAP5: 65.3 -> 65.4No clear effect
add auxiliary score BCE loss (ablation)EPD LOIAlign · WireframesAP5: 65.4 -> 65.7Improved
add EPE loss and binding threshold 10 at test (ablation)HAWPv2 proposals · Wireframe# proposals: 6.19k -> 2.24kImproved
add EPE loss and binding threshold 10 at test (ablation)HAWPv2 · WireframesAP5: 65.5 -> 65.7No clear effect
add distance residual learning (ablation)HAWPv2 · WireframesAP5: 61.1 -> 62.9Improved
add rectified distance maps with residual scales -2 to +2 (ablation)HAWPv2 · WireframesAP5: 62.9 -> 65.7Improved
use unsigned instead of signed residuals (ablation)HAWPv2 · WireframesAP5: 62.6 -> 62.9Improved
use HAWPv2 instead of AFM++ on heatmap F scoreHAWPv2 · WireframeF^H: 82.8 -> 81.4Hurt

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