AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

AIM: An Auto-Augmenter for Images and Meshes

Vinit Veerendraveer Singh, Chandra Kambhamettu

CVPR 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Neuro-symbolic probabilistic layers · 1 citations (OpenAlex)

Check 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 sample-aware AIM deformationsImage classifiers · CUB-200 and Oxford-IIT Petsaccuracy: 78.3 -> 79.4; 91.6 -> 91.9 (ResNet-18); 83.5 -> 84.0; 93.7 -> 93.7 (EfficientNet-b2)Mixed
Add AIM deformationsMeshNet · MSB and SHREC-11 split-16accuracy: 56.5 -> 67.3; 55.6 -> 63.1Improved
Add AIM deformationsMeshNet++ · MSB and SHREC-11 split-16accuracy: 94.5 -> 95.6; 100 -> 100Mixed
Add AIM deformationsDiffusionNet · Human body mesh segmentationaccuracy: 90.9 -> 91.3Improved
Replace learned AIM deformations with random vertex jitterDiffusionNet · Human body mesh segmentationaccuracy: 90.9 -> 87.9Hurt
Add directional consistency loss (ablation)AIM image classifiers · CUB-200 and Oxford-IIT Petsaccuracy: ResNet-18: 78.7 -> 79.4, 91.3 -> 91.9; ResNet-34: 80.4 -> 79.8, 92.6 -> 93Mixed
Add directional consistency loss (ablation)AIM image classifiers · CUB-200 and Oxford-IIT Petsaccuracy: ResNet-50: 82.3 -> 82.5, 93.5 -> 93.5; EfficientNet-b0: 81.8 -> 82.8, 93.2 -> 93.4Mixed
Add directional consistency loss (ablation)AIM image classifiers · CUB-200 and Oxford-IIT Petsaccuracy: EfficientNet-b1: 83.1 -> 83.1, 93.2 -> 93.0; EfficientNet-b2: 83.3 -> 84, 93.2 -> 93.7Mixed
Use AIM deformations during testing as well as training (ablation)Image classifiers · CUB-200 and Oxford-IIT Petsaccuracy: ResNet-18: 78.8 -> 79.4, 91.7 -> 91.9; ResNet-34: 80.1 -> 80.4, 92.8 -> 93.0; ResNet-50: 82.0 -> 82.5, 93.3 -> 93.5Mixed

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