AI Paper Atlas

Research map / Video / Video segmentation and tracking

SegFlow: Joint Learning for Video Object Segmentation and Optical Flow

Jingchun Cheng, Yi-Hsuan Tsai, Shengjin Wang, Ming-Hsuan Yang

ICCV 2017 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 459 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 the flow branch with bi-directional feature propagation (ablation)SegFlow segmentation branch · DAVIS val (semi-supervised)J mean: 0.724 -> 0.748Improved
add the flow branch with bi-directional feature propagation (ablation)SegFlow segmentation branch · DAVIS val (semi-supervised)T mean (lower is better): 0.250 -> 0.194Improved
add the flow branch (offline only) (ablation)SegFlow segmentation branch · DAVIS val (unsupervised)J mean: 0.654 -> 0.674Improved
add offline training before online fine-tuning (ablation)SegFlow · DAVIS val (SegFlow ablation)J mean: 0.538 -> 0.748Improved
add online fine-tuning with first-frame mask and iterative training (ablation)SegFlow · DAVIS val (SegFlow ablation)J mean: 0.669 -> 0.748Improved
add flow data augmentation by synthesizing the next frame (ablation)SegFlow · DAVIS val (SegFlow ablation)T mean (lower is better): 0.225 -> 0.194Improved
add flow data augmentation (ablation)SegFlow · DAVIS val (SegFlow ablation)J mean: 0.739 -> 0.748Improved
add segmentation data augmentation (ablation)SegFlow without flow, offline · DAVIS val (SegFlow ablation)J mean: 0.606 -> 0.654Improved
average predictions of image and its flipped versionSegFlow · DAVIS valJ mean: 0.748 -> 0.761Improved
replace FlowNetS+ft* with SegFlow (add segmentation branch) for flowFlowNetS · Sintel Final trainaverage endpoint error: 4.26 -> 2.61Improved
replace FlowNetS+ft* with SegFlow for flowFlowNetS · KITTI trainaverage endpoint error: 7.37 -> 4.40Improved
replace FlowNetS+ft (published) with SegFlow for flowFlowNetS · Sintel Clean testaverage endpoint error: 6.16 -> 7.45Hurt

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