AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Images

Nir Barel, Ron A Shapira Weber, Nir Mualem, Shahaf E Finder, Oren Freifeld

ECCV 2024 · Architectures and efficiency › Attention and transformers · approach: Mamba architectures · 2 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 autoencoder pre-training before joint alignment (ablation)SpaceJAM · CUB-200 (3 categories)PCK@0.1: 54.9 -> 73.3Improved
add autoencoder pre-training before joint alignment (ablation)SpaceJAM · SPair-71k (3 categories)PCK@0.1: 56.6 -> 58.1Improved
predict a cascade of 5 small transformations instead of a single large one (ablation)SpaceJAM · SPair-71k (3 categories)PCK@0.1: 43.5 -> 58.1Improved
use cascade of 5 instead of 3 transformations (ablation)SpaceJAM · CUB-200 (3 categories)PCK@0.1: 72.6 -> 73.3Improved
use inverse-compositional loss instead of alignment to an atlas (ablation)SpaceJAM · CUB-200 (3 categories)PCK@0.1: 58.5 -> 73.3Improved
use Lie group parameterization (ablation)SpaceJAM · CUB-200 (3 categories)PCK@0.1: 65.6 -> 73.3Improved
add Lie-algebraic curriculum learning (ablation)SpaceJAM · CUB-200 (3 categories)PCK@0.1: 70.8 -> 73.3Improved
add Lie-algebraic curriculum learning (ablation)SpaceJAM · SPair-71k (3 categories)PCK@0.1: 57.2 -> 58.1Improved
use DINOv2 ViT-L features instead of DINOv1 ViT-SSpaceJAM · SPair-71k (all)PCK@0.10: 37.8 -> 45.7Improved
use lightweight SpaceJAM (16K params, ~6 min) instead of ASIC (7.9M params)joint alignment · SPair-71k (all)PCK@0.10: 36.9 -> 37.8Improved
use SpaceJAM instead of ASIC on CUB-200 3 categoriesjoint alignment · CUB-200 (3 categories)PCK@0.10: 75.9 -> 69.6Hurt

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