AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

"Unitail: Detecting, Reading, and Matching in Retail Scene"

Fangyi Chen, Han Zhang, Zaiwang Li, Jiachen Dou, Shentong Mo, Hao Chen, Yongxin Zhang, Uzair Ahmed, Chenchen Zhu, Marios Savvides

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 17 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 Quad-Centerness (ablation)RetailDet base · Unitail-Det valmAP: 58.3 -> 60.4Improved
add Soft Scale assignment (ablation)RetailDet + QC · Unitail-Det valmAP: 60.4 -> 61.4Improved
add Corner Refinement Module (ablation)RetailDet + QC + SS · Unitail-Det valmAP: 61.4 -> 63.8Improved
add Corner Refinement Module (ablation)RetailDet + QC + SS · Unitail-Det valAP75: 72.6 -> 75.8Improved
train text detector on Unitail instead of SynthText+IC15DBNet · Unitail-OCR text detectionhmean: 0.666 -> 0.819Improved
train text detector on Unitail instead of SynthText+IC15FCENet · Unitail-OCR text detectionhmean: 0.538 -> 0.825Improved
add Unitail to text recognition training dataABINet · Unitail-OCR text recognitionaccuracy: 69.2 -> 77.2Improved
add Unitail to text recognition training dataCRNN · Unitail-OCR text recognitionaccuracy: 40.0 -> 51.4Improved
add text matching to visual classifierEfficientNetV2 · Unitail product matching (Hard)accuracy: 56.49 -> 59.24Improved
add text matching to visual classifierResNet101 · Unitail product matching (Hard)accuracy: 58.37 -> 60.52Improved
add text matching to visual classifierResNet101 · Unitail product matching (General)accuracy: 85.03 -> 86.19Improved
use ResNet101 instead of ResNet50 backboneRetailDet · Unitail-Detg-mAP: 54.7 -> 57.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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