AI Paper Atlas

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

Progressive Large Scale-Invariant Image Matching in Scale Space

Lei Zhou, Siyu Zhu, Tianwei Shen, Jinglu Wang, Tian Fang, Long Quan

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 43 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 scale-invariant similarity metricvocabulary-tree retrieval · OxfordmAP: 0.515 -> 0.562Improved
add scale-invariant similarity metricvocabulary-tree retrieval · HolidaysmAP: 0.607 -> 0.646Improved
add scale-invariant similarity metricvocabulary-tree retrieval · Oxfordretrieval time (s): 840.9 -> 859.6Hurt
add scale-invariant similarity metricbaseline retrieval with no extra technique · Multi-scale retrieval setmAP: 0.397 -> 0.672Improved
add scale-invariant similarity metric on top of WGCbaseline retrieval · Multi-scale retrieval setmAP: 0.440 -> 0.679Improved
add scale-invariant similarity metric on top of PGM+HE+MAbaseline retrieval · Multi-scale retrieval setmAP: 0.554 -> 0.734Improved
use scale-invariant matcher instead of exhaustive SIFT matcherSIFT matching · Mikolajczyk zoom+rotation, pair 5correct matches: 112 -> 178Improved
use scale-invariant matcher instead of exhaustive SIFT matcherSIFT matching · Mikolajczyk zoom+rotationaverage matching time (ms): 59.16 -> 33.26Improved
use scale-invariant matcher instead of exhaustive SIFT matcherSIFT matching · Mikolajczyk viewpoint, pair 3correct matches: 64 -> 91Improved
use scale-invariant matcher under large viewpoint changeSIFT matching · Mikolajczyk viewpoint, pairs 4 and 5correct matches: 0 -> 0No clear effect
use scale-invariant matcher instead of MODSfeature matching · Book-cover set, scale ratio 55feature matches: 0 -> 13Improved
use scale-invariant matcher instead of KVLDfeature matching · Book-cover set, scale ratio 32feature matches: 44 -> 60Improved

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