AI Paper Atlas

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

Embedding Based on Function Approximation for Large Scale Image Search

Thanh-Toan Do, Ngai Man Cheung

TPAMI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 38 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 function-approximation embedding (FAemb) instead of VLAT at same dimensionembedding at n=8 · Holidays and Oxford5kmAP: +1.8% and +3.9%Improved
use FAemb instead of VLAT at n=16, 32embedding · Holidays and Oxford5kmAP: about +3%Improved
use FAemb (n=16, D=15,525) instead of VLAD/Temb (n=128, D=16,256)embedding · HolidaysmAP: +7.5%/+2%Improved
use FAemb (n=16, D=15,525) instead of VLAD/Temb (n=128, D=16,256)embedding · Oxford5kmAP: +8.1%/+5%Improved
use fast closed-form F-FAemb instead of FAembembedding · Holidays/Oxford5k, n=16mAP: 75.8 -> 75.5 (Holidays); 67.7 -> 67.6 (Oxford5k)No clear effect
add rotation normalization (RN) to F-FAemb (n=32)F-FAemb · Holidays and Oxford5kmAP: 77.0 -> 80.7; 70.7 -> 74.2Improved
increase number of anchor points nembedding methods · Holidays and Oxford5kmAPImproved
use F-FAemb +RN instead of Temb+RN at D=7,245/8,064embedding · HolidaysmAP: 77.1 -> 75.5Hurt
use F-FAemb +RN instead of CNN featuresimage representation · Oxford5kmAP: 54.5 -> 74.2Improved
use F-FAemb +RN instead of Temb+RN at short dimensionsshort representation · Holidays+Flickr1MmAP: 49.4 -> 68.5 at D=1,024Improved
use F-FAemb instead of Temb as binary codes (ITQ)binary codes · HolidaysmAP: 57.3 -> 59.7 at 1024 bitsImproved
use F-FAemb instead of Temb at 128 bitsbinary codes · Oxford5kmAP: 27.1 -> 26.4Hurt

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