AI Paper Atlas

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

PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click

Henghui Ding, Scott Cohen, Brian Price, Xudong Jiang

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 53 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 phrase input and attribute attention to click-only model (ablation)PhraseClick · RefCOCO testAIoU (%): 77.93 -> 83.94Improved
add graph cut post-processing (ablation)PhraseClick · RefCOCO testAIoU (%): 83.94 -> 85.02Improved
add clicks to phrase-only input (ablation)PhraseClick · RefCOCO testAIoU (%): 50.98 -> 83.94Improved
add one click to phrase inputPhraseClick · RefCOCO valIoU (%): 50.42 -> 80.02Improved
add phrase input to click-only interactionPhraseClick · user study (interactions to 85% IoU)average interactions: 4.49 -> 3.09Improved
use PhraseClick's attribute attention instead of 5-channel referring methods (CMSA) with one phrase and two clicksPhraseClick · RefCOCO valIoU (%): 70.02 -> 84.56Improved
add phrase as second interaction instead of click-only baselines (FCTSFN) on PASCAL VOCPhraseClick · PASCAL VOCnumber of interactions: 4.58 -> 3.12Improved

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