AI Paper Atlas

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

Compositing-aware Image Search

Hengshuang Zhao, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Brian Price, Jiaya Jia

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 19 citations (OpenAlex)

Read the paper

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
extend triplets with top-10 retrieved foregrounds chosen by combined semantic and shape criteria (ablation)Basic triplet training · Compositing evaluation setmean MAP: 38.26 -> 45.70Improved
use shape-only triplet extension (ablation)Basic triplet training · Compositing evaluation setmean MAP: 38.26 -> 35.81Hurt
use semantic-context triplet extension (ablation)Basic triplet training · Compositing evaluation setmean MAP: 38.26 -> 44.18Improved
add shape to semantic triplet extension (ablation)Semantics extension · Compositing evaluation setmean MAP: 44.18 -> 45.70Improved
add MCB module with 20480 output dimension (ablation)Shared network · Compositing evaluation setmean MAP: 46.02 -> 48.42Improved
increase MCB dimension from 20480 to 40960 (ablation)MCB · Compositing evaluation setmean MAP: 48.42 -> 47.91No clear effect
use two-stage training instead of one-stage (ablation)CAIS · Compositing evaluation setmean MAP: 44.65 -> 48.42Improved
use MCB-based compact network instead of separate per-category modules (ablation)CAIS · Compositing evaluation setmean MAP: 48.69 -> 48.42No clear effect
use CAIS instead of classification-feature searchClassification feature · Compositing evaluation setmean MAP: 36.78 -> 48.42Improved
use CAIS instead of classification feature in user studyClassification feature · User studypreference: 70.38Improved
shape feature on car categoryClassification feature · Compositing evaluation set (car)MAP: 14.93 -> 34.77Mixed

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