AI Paper Atlas

Research map / 3D vision / 3D generation

Partially View-aligned Clustering

Zhenyu Huang, Peng Hu, Joey Tianyi Zhou, Jiancheng Lv, Xi Peng

NeurIPS 2020 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations · 46 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 PVC with differentiable alignment instead of PCA+Hungarian alignment followed by best baselinemulti-view clustering · ReutersNMI (%): 16.79 -> 27.99Improved
use PVC instead of best baseline with PCA+Hungarian alignmentmulti-view clustering · Caltech101-20NMI (%): 60.84 -> 65.39Improved
use PVC instead of best baseline with PCA+Hungarian alignmentmulti-view clustering · Scene-15NMI (%): 37.47 -> 39.33Improved
use PVC instead of best baseline with PCA+Hungarian alignmentmulti-view clustering · Pascal SentencesNMI (%): 65.19 -> 72.33Improved
PVC with partial alignment versus baselines given fully ground-truth aligned dataPVC · ReutersNMI (%): 27.47 -> 27.99Improved
PVC with partial alignment versus baselines given fully ground-truth aligned dataPVC · Pascal SentencesACC (%): 69.67 -> 62.67Hurt
remove alignment module (lambda = 0) (ablation)PVC · ReutersACC and NMIHurt
increase lambda beyond 100 (ablation)PVC · ReutersACC and NMIHurt
increase alignment ratio from partial to 100% (ablation)PVC · ReutersACC and NMIMixed

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