AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings

Anita Rau, Guillermo Garcia-Hernando, Danail Stoyanov, Gabriel J. Brostow, Daniyar Turmukhambetov

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 25 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
use box embeddings with asymmetric overlap instead of symmetric vector embeddingsoverlap prediction · Overlap prediction, Notre-DameL1 error: 0.244 -> 0.070Improved
use box embeddings instead of vectorsoverlap prediction · Overlap prediction, Big Benaccuracy (error < 0.1): 24.8% -> 82.6%Improved
use box embeddings instead of vectorsoverlap prediction · Overlap prediction, VeniceRMSE: 0.193 -> 0.112Improved
use box embeddings instead of vectorsoverlap prediction · Overlap prediction, Florenceaccuracy (error < 0.1): 76.5% -> 89.7%Improved
use surface overlap instead of frustum overlap for vector embeddings (ablation)retrieval for localization · 7Scenes localization, Stairsmedian translation error (m): 1.82 -> 0.22Improved
use surface overlap instead of frustum overlap for vector embeddings (ablation)retrieval for localization · 7Scenes localization, Chessmedian rotation error (deg): 1.25 -> 1.19Improved
use box embeddings instead of symmetric vector embeddingsretrieval for localization · 7Scenes localization, Stairsmedian translation error (m): 0.22 -> 0.50Hurt
use box embeddings instead of symmetric vector embeddingsretrieval for localization · 7Scenes localization, Chessmedian translation error (m): 0.04 -> 0.05No clear effect
pre-scale images using predicted relative scale before matchingbox embeddings · Notre-Dame and Big Ben pose estimationrotation errorImproved

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