AI Paper Atlas

Research map / Point clouds / Point cloud classification

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

Xuanyu Yi, Jiajun Deng, Qianru Sun, Xian-Sheng Hua, Joo-Hwee Lim, Hanwang Zhang

ICCV 2023 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 8 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
apply InvJoint training instead of PointCLIPInvJoint · ModelNet40 1-shotaccuracy (%): 52.96 -> 68.85Improved
naive late-fusion ensemble of 2D PointCLIP and 3D DGCNNPointCLIP · ModelNet40 1-shotaccuracy (%): 52.96 -> 53.70No clear effect
add joint hard sample selection (Step 1) (ablation)InvJoint · ModelNet40 16-shotaccuracy (%): 83.91 -> 88.97Improved
add cross-modal invariance learning (Step 2) (ablation)InvJoint · ModelNet40 16-shotaccuracy (%): 85.82 -> 88.97Improved
add both Step 1 and Step 2 over plain CE training with product fusion (ablation)InvJoint · ModelNet40 16-shotaccuracy (%): 81.09 -> 88.97Improved
use product fusion instead of sum fusion (ablation)InvJoint · ModelNet40 16-shotaccuracy (%): 87.61 -> 88.97Improved
use learnable prompt tokens instead of handcrafted templates (ablation)InvJoint · Toys4K 16-shotaccuracy (%): 93.52 -> 78.57Hurt
joint prediction reduces sensitivity to prompt design (ablation)InvJoint · Toys4K 16-shotstd across prompts (%): 10.87 -> 5.51Improved
use ViT-B/16 instead of RN50 visual encoder (ablation)InvJoint · ModelNet40 16-shotaccuracy (%): 85.93 -> 88.97Improved
use InvJoint instead of plain late fusion (ablation)InvJoint · ModelNet40accuracy (%): +4.7% on averageImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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