AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Attention-Based Query Expansion Learning

Albert Gordo, Filip Radenovic, Tamara Berg

ECCV 2020 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 41 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 self-attention encoders instead of fully-connected layers (ablation)LAttQE · ROxford/RParis M/H meanmean mAP: 66.0 -> 70.0Improved
add self-attention instead of fully-connected layers (ablation)LAttQE · ROxford (Hard)mAP: 41.5 -> 49.6Improved
add positional encoding (ablation)LAttQE · ROxford (Hard)mAP: 33.2 -> 49.6Improved
add positional encoding (ablation)LAttQE · RParis (Hard)mAP: 73.4 -> 70.6Hurt
add positional encoding (ablation)LAttQE · ROxford/RParis M/H meanmean mAP: 63.2 -> 70.0Improved
add image embedding to the weighting (not position-only) (ablation)LAttQE · ROxford (Hard)mAP: 42.9 -> 49.6Improved
add image embedding to the weighting (not position-only) (ablation)LAttQE · RParis (Hard)mAP: 66.7 -> 70.6Improved
add auxiliary classification loss (ablation)LAttQE · ROxford/RParis M/H meanmean mAP: 68.5 -> 70.0Improved
add auxiliary classification loss (ablation)LAttQE · ROxford (Hard)mAP: 47.0 -> 49.6Improved
apply LAttQE query expansion vs none (ablation)LAttQE · ROxford (Hard)mAP: 44.3 -> 49.6Improved
add database-side augmentation LAttDBA to LAttQELAttQE · ROxford/RParis (+R1M) meanmAP (mean): 59.8 -> 63.1Improved
LAttQE vs alphaQE on ROxford Hardquery expansion · ROxford (Hard)mAP: 44.5 -> 49.6Improved

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