AI Paper Atlas

Research map / Video / Video segmentation and tracking

Joint Inductive and Transductive Learning for Video Object Segmentation

Yunyao Mao, Ning Wang, Wengang Zhou, Houqiang Li

ICCV 2021 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 108 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 induction branch to the transduction branch (ablation)JOINT · YouTube-VOS 2018 valOverall: 81.2 -> 83.1Improved
add the induction branch to the transduction branch (ablation)JOINT · YouTube-VOS 2018 val unseen categoriesJ unseen: 75.1 -> 78.7Improved
add the induction branch to the transduction branch (ablation)JOINT · YouTube-VOS 2018 val unseen categoriesF unseen: 83.2 -> 86.5Improved
add the transduction branch to the induction branch (LWL) (ablation)JOINT · YouTube-VOS 2018 valOverall: 81.5 -> 83.1Improved
add the transduction branch to the induction branch (LWL) (ablation)JOINT · YouTube-VOS 2018 valseconds per frame: 0.15 -> 0.25Hurt
use a two-head label encoder instead of single-head (ablation)JOINT · YouTube-VOS 2018 valOverall: 81.8 -> 82.4Improved
add the cosine similarity disentangling loss to the two-head encoder (ablation)JOINT · YouTube-VOS 2018 valOverall: 82.4 -> 83.1Improved
add the cosine disentangling loss (ablation)JOINT · YouTube-VOS 2018 val unseenJ unseen: 77.6 -> 78.7Improved
add the cosine disentangling loss (ablation)JOINT · YouTube-VOS 2018 val seenJ seen: 81.1 -> 81.5Improved
use the joint model rather than the induction-only LWL on DAVIS 2017 (YouTube-VOS training)JOINT · DAVIS 2017 valJ&F: 81.6 -> 83.5Improved
use the joint model rather than the induction-only LWL on DAVIS 2017 (DAVIS only training)JOINT · DAVIS 2017 val (DAVIS-only)J&F: 74.3 -> 78.6Improved
compare seen-category score against multi-scale CFBIJOINT · YouTube-VOS 2018 val seenJ seen: 82.2 -> 81.5Hurt

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