AI Paper Atlas

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

Greedy Structure Learning of Hierarchical Compositional Models

Adam Kortylewski, Aleksander Wieczorek, Mario Wieser, Clemens Blumer, Sonali Parbhoo, Andreas Morel-Forster, Volker Roth, Thomas Vetter

CVPR 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 11 citations (OpenAlex)

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
learn the hierarchical structure instead of specifying it a-prioriOURS versus HABM · Four Domain unsupervised domain adaptationclassification score: OURS scores are higher in six out of eight experimentsImproved
learn the hierarchical structure instead of specifying it a-prioriOURS versus HABM · Four Domain unsupervised, D → A and D → Wclassification score: 34.6 $\pm$ 3.7 vs 33.1 $\pm$ 2.4; 68.2 $\pm$ 2.9 vs 65.6 $\pm$ 3.8Hurt
learn the hierarchical structure instead of specifying it a-prioriOURS versus other methods · Four Domain semi-supervised domain adaptationclassification score: OURS scores are higher in five out of eight experimentsImproved
compose two parts at each hierarchy layer rather than changing the number composed (ablation)greedy structure learning scheme · Four Domain classification experimentsclassification scoreNo clear effect
use a single holistic object model instead of multiple templatesOURS · Four Domain unsupervised, DSLR sourceclassification scoreHurt

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