AI Paper Atlas

Research map / Benchmarks / ModelNet40 10-way 20-shot

ModelNet40 10-way 20-shot leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ModelNet40 10-way 20-shot. Best accuracy: 96.8 (Point-MAE + Ours(C), ICML 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ModelNet40 10-way 20-shot · accuracy

15 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
196.8Point-MAE + Ours(C)
Point-MAE
Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding
ICML 2025 · Table 3
Point cloud classification
296.7PointRWKVPointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning
AAAI 2025 · Table 2
Point cloud classification
396.1StruMamba3DStruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
ICCV 2025 · Table 3
Point cloud classification
495.9PCP-MAEPCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
NeurIPS 2024 · Few-shot results table
Point cloud classification
595.8Point-FEMAE
Point-MAE
Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoders
AAAI 2024 · Table: Few-shot Learning
Point cloud classification
695.7MaskFeat3D
Transformer
3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
ICLR 2024 · Few-shot classification table
Point cloud classification
795.5I2P-MAE
ViT-Base CLIP
Learning 3D Representations From 2D Pre-Trained Models via Image-to-Point Masked Autoencoders
CVPR 2023 · Table: Few-shot Classification
Point cloud classification
895.4VPP (ours)VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation
NeurIPS 2023 · Table 5
Shape and surface completion
995.3APPT (2D)
ViT-B
Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis
TPAMI 2026 · Table 2
Point cloud classification
1095.2KR-MAEReliable-View 2D-3D Key-Part Aligned Transformer with Reinforced Masking for 3D Point Cloud Understanding
AAAI 2026 · Table 2
Point cloud classification
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.