AI Paper Atlas

Research map / Video / Video segmentation and tracking

In Defense of Online Models for Video Instance Segmentation

Junfeng Wu, Qihao Liu, Yi Jiang, Song Bai, Alan Yuille, Xiang Bai

ECCV 2022 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 131 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 contrastive training instead of ID head, with multi-cues matching (ablation)IDOL · YouTube-VIS 2019 valAP: 30.3 -> 31.8Improved
add contrastive training instead of ID head, with embedding matching (ablation)IDOL · YouTube-VIS 2019 valAP: 33.6 -> 42.5Improved
add contrastive training instead of ID head (ablation)IDOL · OVIS valAP: 11.0 -> 18.4Improved
add optimal transport sample selection (ablation)IDOL · YouTube-VIS 2019 valAP: 42.5 -> 44.8Improved
add optimal transport sample selection (ablation)IDOL · OVIS valAP: 26.7 -> 28.3Improved
use embedding association instead of multi-cues (ablation)IDOL · YouTube-VIS 2019 valAP: 31.8 -> 42.5Improved
use embedding association instead of multi-cues (ablation)IDOL · OVIS valAP: 18.4 -> 26.7Improved
add temporally weighted softmax (ablation)IDOL · YouTube-VIS 2019 valAP: 44.8 -> 46.4Improved
add temporally weighted softmax (ablation)IDOL · OVIS valAP: 28.3 -> 30.2Improved
pretrain contrastive embedding on COCO pseudo key-reference pairsIDOL ResNet-50 · YouTube-VIS 2019 valAP: 46.4 -> 49.5Improved
pretrain contrastive embedding on COCO pseudo key-reference pairsIDOL Swin-L · YouTube-VIS 2019 valAP: 61.5 -> 64.3Improved
increase clip length from 1 to 30 (frame oracle) (ablation)SeqFormer · OVIS valAP: 32.0 -> 8.9Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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