AI Paper Atlas

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

Breaking Bad: A Dataset for Geometric Fracture and Reassembly

Silvia Sellán, Yun-Chun Chen, Ziyi Wu, Animesh Garg, Alec Jacobson

NeurIPS 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 16 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 DGL (graph network) instead of Global or LSTMshape assembly baselines · everyday subsetpart accuracy: 24.6 -> 31.0Improved
test on objects with more fractured pieces (21-50 vs 2-20) (ablation)DGL trained on 2-20 pieces · everyday subsetpart accuracy: 31.0 -> 7.5Hurt
train on 2-50 pieces instead of 2-20 (ablation)DGL · everyday, test 51-100 pieceschamfer distance: 23.0 -> 18.1Improved
train on 2-100 pieces instead of 2-20 (ablation)DGL · everyday, test 51-100 pieceschamfer distance: 23.0 -> 13.9Improved
train on 2-100 pieces instead of 2-20 (ablation)DGL · everyday, test 2-20 piecespart accuracy: 31.0 -> 29.4Hurt
fine-tune from everyday-subset pre-trained model instead of training from scratch (ablation)DGL · artifact subsetpart accuracy: 12.8 -> 19.4Improved
fine-tune from everyday-subset pre-trained model instead of training from scratch (ablation)LSTM · artifact subsetpart accuracy: 6.6 -> 11.7Improved
fine-tune from everyday-subset pre-trained model instead of training from scratch (ablation)Global · artifact subsetpart accuracy: 12.7 -> 13.3Improved
pre-train on everyday plus artifact data rather than everyday only, test on unseen subset (ablation)DGL · other subsetchamfer distance: 38.5 -> 36.6Improved
test semantic-assembly methods on geometric fracture reassembly vs semantic assemblyGlobal, LSTM, DGL · Breaking BadperformanceHurt

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