AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning What to Learn for Video Object Segmentation

Goutam Bhat, Felix Järemo Lawin, Martin Danelljan, Andreas Robinson, Michael Felsberg, Luc Van Gool, Radu Timofte

ECCV 2020 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation

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 end-to-end training through the few-shot learner (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 74.5 -> 77.5Improved
add learned label generator (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 77.5 -> 78.9Improved
add learned importance weight predictor (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 78.9 -> 79.8Improved
initialize backbone with Mask-RCNN weights instead of ImageNet (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 78.6 -> 79.8Improved
use Lovasz loss instead of binary cross-entropy (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 79.2 -> 79.8Improved
use long training instead of short training (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 79.8 -> 81.2Improved
use mask encoding with D>=4 channels instead of 1 (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: +2.0Improved
perform one steepest-descent update per frame instead of none (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: more than 5 pointsImproved
use more than 3 steepest-descent iterations per frame (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 81.2 -> slight degradationHurt
evaluate on local search region instead of full frame (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 80.2 -> 81.2Improved
use update rate 0.1 for global importance weights (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJ: 81.2Improved
increase maximum training set size K_max up to 16 (ablation)Few-shot VOS · YouTube-VOS 2019 train split, 300-video validationJMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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