AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Discovering Design Concepts for CAD Sketches

Yuezhi Yang, Hao Pan

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 5 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 concept-based generation rather than autoregressive generationCAD sketch image-conditioned generation · Image-conditioned generationPrimitive F-score: 0.575 -> 0.711Improved
use concept-based generation rather than autoregressive generationCAD sketch image-conditioned generation · Image-conditioned generationConstraint F-score: 0.301 -> 0.368Improved
add binary reference costs to reconstruction loss (ablation)Sketch concept induction · SketchGraphs auto-encodingConstraint F-score: 0.290 -> 0.766Improved
add sharp reference loss (ablation)Sketch concept induction · SketchGraphs auto-encodingConstraint F-score: 0.104 -> 0.766Improved
add modularity enhancement bias loss (ablation)Sketch concept induction · SketchGraphs auto-encodingModular(%): 13.3 -> 50.8Improved
increase concept query count from 5 to 12 (ablation)Sketch concept induction · SketchGraphs auto-encodingConstraint F-score: 0.766 -> 0.918Improved
increase concept query count from 5 to 12 (ablation)Sketch concept induction · SketchGraphs auto-encodingModular(%): 50.8 -> 14.9Hurt
increase argument count from 2 to 4 (ablation)Sketch concept induction · SketchGraphs auto-encodingModular(%): 50.8 -> 7.1Hurt
decrease argument count from 2 to 1 (ablation)Sketch concept induction · SketchGraphs auto-encodingConstraint F-score: 0.766 -> 0.666Hurt
increase concept library size from 50 to 2000 (ablation)Sketch concept induction · SketchGraphs auto-encodingConstraint F-score: 0.581 -> 0.779Improved
increase concept library size from 50 to 2000 (ablation)Sketch concept induction · SketchGraphs auto-encodingModular(%): 48.1 -> 50.6No clear effect

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