AI Paper Atlas

Research map / Video / Video segmentation and tracking

Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation

Feng Zhu, Zongxin Yang, Xin Yu, Yi Yang, Yunchao Wei

ECCV 2022 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 10 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 identification and association modules together (ablation)CondInst image model · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 24.0 -> 37.9Improved
add identification module without association (ablation)CondInst image model · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 24.0 -> 12.6Hurt
add association module without identification (ablation)CondInst image model · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 24.0 -> 24.5No clear effect
add global memory to HAB (ablation)IAI HAB · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 5.0 mAPImproved
add local memory to HAB (ablation)IAI HAB · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 3.0 mAPImproved
add classification projector to HAB (ablation)IAI HAB · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 36.9 -> 37.9Improved
use IAI paradigm instead of tracking-by-detection with Mask R-CNNMask R-CNN · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 30.3 -> 31.7Improved
use IAI paradigm instead of tracking-by-detection with CondInstCondInst · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 32.1 -> 37.9Improved
use focal loss instead of cross-entropy for ID loss (ablation)IAI+CondInst · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 36.4 -> 37.9Improved
use 3-conv instead of 2-conv ID head (ablation)IAI+CondInst · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 37.9 -> 38.1No clear effect
use 4-conv instead of 2-conv ID head (ablation)IAI+CondInst · YouTube-VIS-2019 val (ablation, R50 no aug)mAP: 37.9 -> 35.3Hurt
pretrain on YouTube-VIS 2019 before OVIS trainingIAI+CondInst · OVIS valmAP: 18.5 -> 20.6Improved

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