atlas

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

Weakly Supervised Semantic Segmentation Using Web-Crawled Videos

CVPR 2017 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 150 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use separate image-based encoder training and video-based segmentation training rather than learning the whole model directly from videosWeakly supervised semantic segmentation · PASCAL VOC 2012 valmIoUHelped
Replace the [cite] video set with automatically collected YouTube videos (ablation)Ours · PASCAL VOC 2012 valmIoU: 49.2 -> 55.2Helped
Add domain adaptation by generating image segmentation labels and fine-tuning on still images (ablation)Ours with YouTube videos · PASCAL VOC 2012 valmIoU: 55.2 -> 58.1Helped
Use web-video-generated segmentation supervision with image-level labelsWeakly supervised semantic segmentation · PASCAL VOC 2012 valmIoU: 50.7 -> 58.1Helped

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