AI Paper Atlas

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

Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)

Danna Gurari, Kun He, Bo Xiong, Jianming Zhang, Mehrnoosh Sameki, Suyog Dutt Jain, Stan Sclaroff, Margrit Betke, Kristen Lorraine Grauman

IJCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 15 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
fine-tune the SOS network on STATIC ambiguity labels instead of using SOS as isambiguity classifier · seven CV benchmarksaverage precision: 85.7% -> 90.7%Improved
use CNN-FT instead of Feng et al. saliency detectorambiguity classifier · VizWiz imagesaverage precision: 54.2% -> 64.6%Improved
apply the classifier to blind-photographer VizWiz images instead of curated benchmark imagesCNN-FT · ambiguity prediction APaverage precision: 90.7% -> 64.6%Hurt
ask crowd judgers directly about ambiguity instead of collecting multiple drawn segmentationsambiguity labeling · Weizmannlabel agreement: matches labels for 79% of images with over 10x less effort (4.7 vs 50 seconds)Improved
exclude ambiguous images from evaluationsegmentation algorithm benchmarking · Weizmanntop-performing method: 19 of the images are labeled as ambiguous; top method switchesMixed
allocate redundant segmentations by predicted ambiguity instead of baselinescrowdsourcing pipeline · 800 images, region-based measureeffort to capture diversity: accelerates collection of ~51% of diversity by at least 27%Improved
allocate redundant segmentations by predicted ambiguity instead of baselinescrowdsourcing pipeline · 800 images, boundary-based measureeffort to capture diversity: accelerates collection of ~53% of diversity by as much as 47%Improved
capture most of total diversity (about 70%)ambiguity-guided allocation · 800 imagesgain over baselines: gains taper at ~70% of total diversityNo clear effect

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