Invariant training 2D-3D joint hard samples for few-shot point cloud recognition

We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by using a joint prediction from a conventional 3D model and a well-pretrained 2D model. Surprisingly, such an ensemble, though seems trivial, has hardly been shown effective in recent 2D-3D models. We find out t...

Full description

Saved in:
Bibliographic Details
Main Authors: YI, Xuanyu, DENG, Jiajun, SUN, Qianru, HUA, Xian-Sheng, LIM, Joo-Hwee, ZHANG, Hanwang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8389
https://ink.library.smu.edu.sg/context/sis_research/article/9392/viewcontent/Yi_Invariant_Training_2D_3D_Joint_Hard_Samples_for_Few_Shot_Point_Cloud_ICCV_2023_paper__1_.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by using a joint prediction from a conventional 3D model and a well-pretrained 2D model. Surprisingly, such an ensemble, though seems trivial, has hardly been shown effective in recent 2D-3D models. We find out the crux is the less effective training for the “joint hard samples”, which have high confidence prediction on different wrong labels, implying that the 2D and 3D models do not collaborate well. To this end, our proposed invariant training strategy, called INVJOINT, does not only emphasize the training more on the hard samples, but also seeks the invariance between the conflicting 2D and 3D ambiguous predictions. INVJOINT can learn more collaborative 2D and 3D representations for better ensemble. Extensive experiments on 3D shape classification with widely-adopted ModelNet10/40, ScanObjectNN and Toys4K, and shape retrieval with ShapeNet-Core validate the superiority of our INVJOINT.