AI Paper Atlas

Research map / 3D vision / Face and shape

Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning

Ming-Xian Lin, Jie Yang, He Wang, Yu-Kun Lai, Rongfei Jia, Binqiang Zhao, Lin Gao

ICCV 2021 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 41 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 category-level contrastive loss (ablation)Ours · Pix3DAccTop-1: 75.2% -> 78.9%Improved
add category-level contrastive loss (ablation)Ours · Pix3DAccCats: 95.9% -> 96.1%No clear effect
use color transfer instead of only affine augmentation (ablation)Ours · Pix3DAccTop-1: 75.2% -> 78.9%Improved
use color transfer instead of only affine augmentation (ablation)Ours · Comp CarsAccTop-1: 67.3% -> 77.8%Improved
use color transfer instead of only affine augmentation (ablation)Ours · Stanford CarsAccTop-1: 81.7% -> 83.4%Improved
use color transfer instead of HSV augmentation (ablation)Ours · Pix3DAccTop-1: 76.6% -> 78.9%Improved
use color transfer instead of HSV augmentation (ablation)Ours · Comp CarsAccTop-1: 73.0% -> 77.8%Improved
use HSV augmentation instead of only affine augmentationOurs · Stanford CarsAccTop-1: 81.7% -> 81.5%Hurt
use contrastive instance loss instead of triplet loss with category supervision (ablation)Ours · Pix3DAccTop-1: 66.5% -> 78.9%Improved
use contrastive instance loss instead of triplet loss (ablation)Ours · Comp CarsAccTop-1: 64.0% -> 77.8%Improved
use contrastive instance loss instead of triplet loss (ablation)Ours · Stanford CarsAccTop-1: 80.3% -> 83.4%Improved
include ground-truth shape in category loss positives (ablation)Ours · Pix3DAccTop-1: 76.7% -> 78.9%Improved

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