AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

FeaBoost: Joint Feature and Label Refinement for Semantic Segmentation

Yulei Niu, Zhiwu Lu, Songfang Huang, Xin Gao, Ji-Rong Wen

AAAI 2017 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 4 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 one-vs-all SVM trained on refined labelsFeaBoost · MSRCaccuracy (%): 77 -> 78Improved
add one-vs-all SVM trained on refined labelsFeaBoost · LabelMeaccuracy (%): 39 -> 42Improved
weakly supervised FeaBoost versus Niu et al. 2015 low-rank factorizationFeaBoost · MSRCaccuracy (%): 71 -> 77Improved
FeaBoost+SVM versus fully supervised Russell et al. 2009FeaBoost+SVM · MSRCaccuracy (%): 75 -> 78Improved
FeaBoost+SVM versus Li et al. 2015 and Xu et al. 2015FeaBoost+SVM · LabelMeaccuracy (%): 41 -> 42Improved
add 1 random noisy label to 100% of imagesFeaBoost · LabelMeaccuracy (%): 47 -> 35Hurt
add 2 random noisy labels to 100% of imagesFeaBoost · LabelMeaccuracy (%): 47 -> 24Hurt
add 3 random noisy labels to 100% of imagesFeaBoost · LabelMeaccuracy (%): 47 -> 20Hurt
FeaBoost versus Li et al. 2015 under noise r=1, p=100FeaBoost · LabelMeaccuracy (%): 30 -> 35Improved
FeaBoost versus Niu et al. 2015 under noise r=3, p=100FeaBoost · LabelMeaccuracy (%): 18 -> 20Improved
FeaBoost with clean labels versus Li et al. 2015FeaBoost · LabelMeaccuracy (%): 41 -> 47Improved
FeaBoost with clean labels versus Niu et al. 2015FeaBoost · LabelMeaccuracy (%): 33 -> 47Improved

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