AI Paper Atlas

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

Exploring 3D Dataset Pruning

Xiaohan Zhao, Xinyi Shang, Jiacheng Liu, Zhiqiang Shen

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 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
use KD soft labels instead of hard labels under rebalancing policies (ablation)PointNet++ on FL-RBF subset · ShapeNet55OA: 79.10 -> 81.82Improved
use KD soft labels instead of hard labels under rebalancing policies (ablation)PointNet++ on FL-RBF subset · ShapeNet55mAcc: 60.47 -> 64.24Improved
select with embedding geometry rather than scalar scores (Loss) (ablation)subset selection · ShapeNet55head/tail score overlap: 26% -> 96%Improved
select with embedding geometry rather than scalar scores (Loss) (ablation)subset selection · ShapeNet55selection imbalance ratio: 40.94x -> 1.88xImproved
add seeded stratified floor (k=0.6) to FL-RBF (ablation)FL-RBF · ShapeNet55 (m=550)mAcc: +8.13Improved
add seeded stratified floor (k=0.4) to FL-RBF (ablation)FL-RBF · ShapeNet55 (m=1100)OA: -0.30No clear effect
add seeded stratified floor (k=0.4) to FL-RBF (ablation)FL-RBF · ShapeNet55 (m=1100)mAcc: +4.65Improved
add seeded stratified floor (k=0.4) to FL-RBF (ablation)FL-RBF · ScanObjectNN (m=150)mAcc: +3.34Improved
add seeded stratified floor (k=0.4) to FL-RBF (ablation)FL-RBF · ModelNet40 (m=1600)OA: -0.24No clear effect
add seeded stratified floor (k=0.6) to FL-RBF (ablation)FL-RBF · ShapeNet55 (m=1100)OA: -1.82Hurt
add seeded stratified floor (k=0.6) to FL-RBF (ablation)MeshMAE FL-RBF · ModelNet40 mesh (m=400)mAcc: +2.48Improved
add seeded stratified floor (k=0.4) to FL-RBF (ablation)MeshMAE FL-RBF · ModelNet40 mesh (m=400)OA: -0.58Hurt

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