AI Paper Atlas

Research map / Point clouds / Point cloud classification

Canonical Shape Projection is All You Need for 3D Few-shot Class Incremental Learning

Ali Cheraghian, Zeeshan Hayder, Sameeea Ramasinghe, Shafin Rahman, Javad Jafaryahya, Lars Petersson, Mehrtash Harandi

ECCV 2024 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 4 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
add the learned rotation (canonical projection) loss Lc on top of Lr (ablation)C3PR · ShapeNet -> ScanObjectNNrelative accuracy drop Delta: 22.9 -> 17.3Improved
add gradient consistency loss Lg on top of Lr (ablation)C3PR · ShapeNet -> ScanObjectNNrelative accuracy drop Delta: 22.9 -> 20.6Improved
add Lg on top of Lr + Lc (ablation)C3PR · ShapeNet -> ScanObjectNNrelative accuracy drop Delta: 17.3 -> 14.9Improved
add module C background reprogramming (ablation)C3PR · ShapeNet -> ScanObjectNNrelative accuracy drop Delta: 18.4 -> 14.9Improved
use consistent-background reprogramming instead of conventional reprogramming (ablation)C3PR · ShapeNet -> ScanObjectNNrelative accuracy drop Delta: 17.3 -> 14.9Improved
replace ten fixed camera depth maps (PointCLIP v2) with one learned projection (ablation)C3PR · ShapeNet -> ScanObjectNNaccuracy per taskImproved
use multiple GPT-generated prompts per class instead of one fixed prompt (ablation)C3PR · ShapeNet -> ScanObjectNNaccuracy per taskImproved
apply learned projection and reprogramming to point cloud classificationCurveNet · ModelNet40 classificationaccuracy: 93.8 -> 94.6Improved
train on synthetic base classes then few-shot real-scanned classes (domain gap)C3PR · cross-dataset vs within-datasetrelative accuracy drop DeltaHurt

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