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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add the finetuning stage after COCO+video main-training (ablation) | Seq Mask R-CNN · YouTube-VIS val | AP: 46.2 -> 47.6 | Improved |
| add the finetuning stage after COCO+video main-training (ablation) | Seq Mask R-CNN · DAVIS-UVOS val | J&F: 67.3 -> 70.4 | Improved |
| add COCO-mixed main-training before finetuning (ablation) | Seq Mask R-CNN · YouTube-VIS val | AP: 40.8 -> 47.6 | Improved |
| add COCO-mixed main-training before finetuning (ablation) | Seq Mask R-CNN · DAVIS-UVOS val | J&F: 48.9 -> 70.4 | Improved |
| add sequence reduction (NMS over sequences) (ablation) | Seq Mask R-CNN ResNet-101 · YouTube-VIS val | AP: 19.3 -> 43.8 | Improved |
| add sequence reduction (NMS over sequences) (ablation) | Seq Mask R-CNN ResNeXt-101 · YouTube-VIS val | AP: 20.7 -> 47.6 | Improved |
| add sequence reduction (NMS over sequences) (ablation) | Seq Mask R-CNN ResNeXt-101 · YouTube-VIS val | AR@100: 58.1 -> 56.0 | Hurt |
| add sequence reduction (NMS over sequences) (ablation) | Seq Mask R-CNN ResNet-101 · YouTube-VIS val | AR@100: 55.1 -> 53.2 | Hurt |
| add sequence reduction (NMS over sequences) (ablation) | Seq Mask R-CNN ResNet-101 · DAVIS-UVOS val | J-Mean: 62.4 -> 65.0 | Improved |
| add sequence reduction (NMS over sequences) (ablation) | Seq Mask R-CNN ResNeXt-101 · DAVIS-UVOS val | F-Mean: 70.9 -> 73.8 | Improved |
| add category-aware reduction (ablation) | Seq Mask R-CNN ResNet-50 · YouTube-VIS val | AP: 40.4 -> 41.5 | Improved |
| add category-aware reduction (ablation) | Seq Mask R-CNN ResNet-101 · YouTube-VIS val | AP: 43.8 -> 45.1 | Improved |
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.
- STEm-Seg — STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (ECCV 2020) · better on 3 of 3 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
- End-to-End Video Instance Segmentation With Transformers (CVPR 2021 · similarity 0.93)
- Efficient Video Instance Segmentation via Tracklet Query and Proposal (CVPR 2022 · similarity 0.92)
- InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation (NeurIPS 2022 · similarity 0.91)
- InstanceFormer: An Online Video Instance Segmentation Framework (AAAI 2023 · similarity 0.91)
- SyncVIS: Synchronized Video Instance Segmentation (NeurIPS 2024 · similarity 0.88)
- Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation (CVPR 2025 · similarity 0.88)
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.
