AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Few-Shot Class-Incremental Learning for 3D Point Cloud Objects

Townim Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi, Morteza Saberi, Shafin Rahman

ECCV 2022 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation

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 Microshape features (with language prototypes) (ablation)FSCIL with PointNet · ShapeNet to CO3D FSCILfinal-task accuracy: 53.6 -> 57.1Improved
add Microshape features (with feature prototypes) (ablation)FSCIL with PointNet · ShapeNet to CO3D FSCILfinal-task accuracy: 51.8 -> 53.4Improved
use language prototypes instead of feature prototypes (ablation)FSCIL with Microshape · ShapeNet to CO3D FSCILfinal-task accuracy: 53.4 -> 57.1Improved
freeze feature extractor during incremental steps (ablation)Microshape FSCIL · ShapeNet to CO3D FSCILfinal-task accuracy: 50.7 -> 57.1Improved
add SVD orthogonalization of k-means centers (ablation)Microshape FSCIL · ShapeNet to CO3D FSCILfinal-task accuracy: 54.6 -> 57.1Improved
use cross-entropy loss instead of MSE in the relation network (ablation)Microshape FSCIL · ShapeNet to CO3D FSCILfinal-task accuracy: 55.2 -> 57.1Improved
increase k-means centroids from 256 to 1024 (ablation)Microshape FSCIL · ShapeNet to CO3D FSCILfinal-task accuracy: 44.8 -> 57.1Improved
increase k-means centroids from 1024 to 2048 (ablation)Microshape FSCIL · ShapeNet to CO3D FSCILfinal-task accuracy: 57.1 -> 57.3No clear effect
increase k-means centroids from 1024 to 4096 (ablation)Microshape FSCIL · ShapeNet to CO3D FSCILfinal-task accuracy: 57.1 -> 57.0No clear effect
add Microshape features and language prototype (ablation)dynamic few-shot learning, 1-shot · ModelNet to ScanObjectNN dynamic few-shotaccuracy: 39.90 -> 72.23Improved
add Microshape features and language prototype (ablation)dynamic few-shot learning, 5-shot · ModelNet to ScanObjectNN dynamic few-shotaccuracy: 51.65 -> 72.53Improved
add Microshape-based backbone (ablation)3D recognition baseline · ModelNet40 to ScanObjectNN recognition (11 common classes)accuracy: 44.25 -> 46.34Improved

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