AI Paper Atlas

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

Learning to Segment Human by Watching YouTube

Xiaodan Liang, Yunchao Wei, Liang Lin, Yunpeng Chen, Xiaohui Shen, Jianchao Yang, Shuicheng Yan

TPAMI 2016 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 22 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 video-context guided mask inference over image-based segmentation (ablation)iterative framework · VOC 2012 val (person)IoU (%): 72.9 -> 81.8Improved
add pairwise potentials (ablation)video-context inference · VOC 2012 val (person)IoU (%): 80.5 -> 81.8Improved
add higher-order potentials (ablation)video-context inference · VOC 2012 val (person)IoU (%): 80.9 -> 81.8Improved
iterate training and mask refinement for 10 iterations (ablation)Ours · VOC 2012 val (person)IoU (%): 28.1 -> 81.8Improved
add sample-weighted loss (ablation)Ours · VOC 2012 val (person)IoU (%): 76.8 -> 81.8Improved
add more negative frames from raw videos (ablation)Ours · VOC 2012 val (person)IoU (%): 74.9 -> 81.8Improved
add sample-weighted loss and negative images together (ablation)Ours · VOC 2012 val (person)IoU (%): 70.3 -> 81.8Improved
add 10k bounding box annotations in last iterationOurs · VOC 2012 val (person)IoU (%): +0.4%No clear effect
add 10k mask annotations in last iterationOurs · VOC 2012 val (person)IoU (%): 81.5 -> 83.0Improved
use EM procedure to drop frames with few foreground pixels (ablation)image-level person-label training · VOC 2012 val (person)IoU (%): 34.2 -> 52.8Improved
use video-context inference instead of image co-localization boxesOurs · VOC 2012 val (person)IoU (%): 40.6 -> 81.5Improved
train on 2-class person task instead of multi-class (ablation)DeepLab-CRF · VOC 2012 test (person)IoU (%): 77.6 -> 76.7Hurt

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