AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

OrthoRF: Exploring Orthogonality in Object-Centric Representations

Despoina Touska, Bastiaan Onne Fagginger Auer, Alexandru Onose, Tejaswi Kasarla, Luis Armando Pérez Rey, Maximilian Lipp, Lyubov Amitonova, Martin R. Oswald, Pascal Cerfontaine

ICLR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Object-centric learning theory and video · 0 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 softmax with centering and orthogonality loss together to Rotating Features (ablation)OrthoRF · 4Shapes (n=5)ARI: 0.9750 -> 0.9995Improved
add orthogonality loss (lambda 0 -> 0.1) on top of softmax with centering (ablation)OrthoRF · 4Shapes (n=5)ARI: 0.6280 -> 0.9995Improved
add softmax with centering on top of orthogonality loss (ablation)OrthoRF · 4Shapes (n=5)ARI: 0.8530 -> 0.9995Improved
evaluate OrthoRF thresholded psi_final instead of k-means on z_final (ablation)OrthoRF · 4Shapes (n=5)MBO_OV_i: 0.8204 -> 0.9832Improved
OrthoRF vs RF under identical k-means post-processing on visible regionsOrthoRF · 4ShapesARI-BG, MBO_iNo clear effect
use large orientation dimension n=20 (ablation)OrthoRF vs RF · 4ShapesARI-BG: RF 0.7129 vs OrthoRF 0.9974Improved
use n smaller than the number of objects (n=2,3) (ablation)OrthoRF vs RF · 4ShapesARI-BG: OrthoRF 0.4987 vs RF 0.667 at n=2Hurt
orthogonality loss weight lambda 0 vs positive for small n (ablation)OrthoRF · 4Shapes (n=5, n=6)ARI: n=5: 0.6279 -> 0.9997 (lambda 0 -> 0.1)Improved
orthogonality loss weight lambda at n=20 (ablation)OrthoRF · 4Shapes (n=20)ARI: lambda 0: 0.9975; lambda 0.1: 0.9988No clear effect
replace RF with OrthoRF on SEM dataOrthoRF · SEM noisyARI-BG: 0.7043 -> 0.8356Improved
replace RF with OrthoRF on Shapes dataset with variable object countOrthoRF · ShapesARI-BG: 0.744 -> 0.833Improved
replace RF with OrthoRF on MNIST&ShapeOrthoRF · MNIST&ShapeARI+BG: ARI-BG 0.972 -> 0.996; ARI+BG 0.699 -> 0.667Mixed

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