AI Paper Atlas

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

Interferences in Match Kernels

Naila Murray, Hervé Jeǵou, Florent Perronnin, Andrew Zisserman

TPAMI 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 29 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
replace sum aggregation with democratic aggregation (ablation)T-embedding + RN · Oxford5kmAP: 63.0 -> 67.0Improved
replace sum aggregation with GMP (ablation)T-embedding + RN · Oxford5kmAP: 63.0 -> 70.0Improved
replace sum aggregation with GMP (ablation)T-embedding + RN · Oxford105kmAP: 55.0 -> 64.4Improved
replace sum aggregation with GMP (ablation)T-embedding + RN · INRIA HolidaysmAP: 73.4 -> 76.5Improved
add rotation and normalisation (RN) (ablation)T-embedding + sum · Oxford5kmAP: 58.1 -> 63.0Improved
add rotation and normalisation (RN) (ablation)T-embedding + GMP · Oxford5kmAP: 63.4 -> 70.0Improved
add rotation and normalisation (RN) (ablation)FV + sum · INRIA HolidaysmAP: 61.7 -> 68.7Improved
replace sum aggregation with GMP (ablation)FV + RN · INRIA HolidaysmAP: 68.7 -> 69.4Mixed
replace sum aggregation with democratic aggregation (ablation)FV · INRIA HolidaysmAP: 61.7 -> 62.1No clear effect
replace FV embedding with T-embedding (ablation)sum aggregation · Oxford5kmAP: 49.5 -> 58.1Improved
reduce T-embedding GMP+RN vector from 8,064 to 128 dimensions (ablation)T-embedding + GMP + RN · Oxford5kmAP: 70.0 -> 42.2Hurt
reduce T-embedding GMP+RN vector from 8,064 to 1,024 dimensions (ablation)T-embedding + GMP + RN · Oxford5kmAP: 70.0 -> 58.3Hurt

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