Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition

TL;DR

This paper introduces InvJoint, a training strategy that enhances 2D-3D ensemble collaboration in few-shot point cloud recognition by focusing on hard samples and enforcing invariance between conflicting predictions, leading to improved performance.

Contribution

Proposes InvJoint, a novel invariant training method that improves 2D-3D ensemble collaboration for few-shot point cloud recognition by emphasizing hard samples and prediction invariance.

Findings

Outperforms existing methods on ModelNet10/40, ScanObjectNN, Toys4K

Improves shape retrieval on ShapeNet-Core

Enhances collaborative learning between 2D and 3D models

Abstract

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-trained 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.