AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video Instance Segmentation With a Propose-Reduce Paradigm

Huaijia Lin, Ruizheng Wu, Shu Liu, Jiangbo Lu, Jiaya Jia

ICCV 2021 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 88 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 finetuning stage after COCO+video main-training (ablation)Seq Mask R-CNN · YouTube-VIS valAP: 46.2 -> 47.6Improved
add the finetuning stage after COCO+video main-training (ablation)Seq Mask R-CNN · DAVIS-UVOS valJ&F: 67.3 -> 70.4Improved
add COCO-mixed main-training before finetuning (ablation)Seq Mask R-CNN · YouTube-VIS valAP: 40.8 -> 47.6Improved
add COCO-mixed main-training before finetuning (ablation)Seq Mask R-CNN · DAVIS-UVOS valJ&F: 48.9 -> 70.4Improved
add sequence reduction (NMS over sequences) (ablation)Seq Mask R-CNN ResNet-101 · YouTube-VIS valAP: 19.3 -> 43.8Improved
add sequence reduction (NMS over sequences) (ablation)Seq Mask R-CNN ResNeXt-101 · YouTube-VIS valAP: 20.7 -> 47.6Improved
add sequence reduction (NMS over sequences) (ablation)Seq Mask R-CNN ResNeXt-101 · YouTube-VIS valAR@100: 58.1 -> 56.0Hurt
add sequence reduction (NMS over sequences) (ablation)Seq Mask R-CNN ResNet-101 · YouTube-VIS valAR@100: 55.1 -> 53.2Hurt
add sequence reduction (NMS over sequences) (ablation)Seq Mask R-CNN ResNet-101 · DAVIS-UVOS valJ-Mean: 62.4 -> 65.0Improved
add sequence reduction (NMS over sequences) (ablation)Seq Mask R-CNN ResNeXt-101 · DAVIS-UVOS valF-Mean: 70.9 -> 73.8Improved
add category-aware reduction (ablation)Seq Mask R-CNN ResNet-50 · YouTube-VIS valAP: 40.4 -> 41.5Improved
add category-aware reduction (ablation)Seq Mask R-CNN ResNet-101 · YouTube-VIS valAP: 43.8 -> 45.1Improved

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