AI Paper Atlas

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

Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning

Hu Han, Jie Li, Anil K. Jain, Shiguang Shan, Xilin Chen

TPAMI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 52 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 joint detection and compact representation learning (multi-task) on top of a Faster R-CNN detectortattoo detector · Tatt-Crecall at 0.1 FPPI: 56.2 -> 61.7Improved
add joint detection and compact representation learning (multi-task)tattoo detector · WebTattoo testrecall at 0.1 FPPI: 80.2 -> 87.1Improved
detect tattoos with Faster R-CNN before SSDH features (ablation)SSDH-VGG16 · WebTattoo searchprecision-recallImproved
use ground-truth tattoo boxes instead of detected boxes for featuresproposed CRL · WebTattoo searchprecision-recallImproved
extract features from final location estimates instead of region proposalsproposed vs OIM-ResNet50 · WebTattoo searchprecision-recallImproved
increase code length from 256 to 512 bits (ablation)proposed · WebTattoo searchprecision: minor precision drop around 60% recallNo clear effect
reduce code length from 256 to 128 bits (ablation)proposed · WebTattoo searchprecision: large drop of precisionHurt
add dispersity loss to cross-entropy loss (ablation)proposed · WebTattoo searchrank-1 accuracy: no rank-1 gain, improves beyond rank-1No clear effect
add polarization loss to cross-entropy and dispersity losses (ablation)proposed · WebTattoo searchrank-1 accuracyImproved
populate gallery with 300K background tattoo imagesall methods · WebTattoo identificationrank-1 accuracy: about 30% degradation at rank-1Hurt
use binary codes with Hamming distance instead of real-valued cosine distanceproposed · 256-D codesmatching time (ms): 0.3 -> 0.06Improved
stitch multiple training images and buffer features to enlarge instance batch for CRLproposed training · tattoo searchtraining convergenceImproved

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