Research map / Video / Video segmentation and tracking
Crossover Learning for Fast Online Video Instance Segmentation
Shusheng Yang, Yuxin Fang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu
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 crossover learning (COL) (ablation) | CondInst-VIS · YouTube-VIS-2019 val | AP: 32.1 -> 33.1 | Improved |
| add global balanced embedding (GBE) (ablation) | CondInst-VIS · YouTube-VIS-2019 val | AP: 32.1 -> 33.5 | Improved |
| add both COL and GBE (ablation) | CondInst-VIS · YouTube-VIS-2019 val | AP: 32.1 -> 34.8 | Improved |
| add crossover learning with large sample interval T=20 (ablation) | CrossVIS · YouTube-VIS-2019 val | AP: 33.4 -> 34.8 | Improved |
| add crossover learning with small sample interval T=1 (ablation) | CrossVIS · YouTube-VIS-2019 val | AP: 33.1 -> 33.6 | Improved |
| use global instead of pair-wise embedding (CE loss) (ablation) | instance association · YouTube-VIS-2019 val | AP: 33.1 -> 33.4 | Improved |
| use focal loss instead of CE for pair-wise embedding (ablation) | instance association · YouTube-VIS-2019 val | AP: 33.1 -> 33.3 | No clear effect |
| use global embedding with focal loss instead of pair-wise CE (ablation) | instance association · YouTube-VIS-2019 val | AP: 33.1 -> 34.8 | Improved |
| use global instead of pair-wise embedding for stability (CE) (ablation) | instance association · YouTube-VIS-2019 val | AP std: 0.78 -> 0.27 | Improved |
| add multi-scale training | CrossVIS · YouTube-VIS-2019 val | AP: 34.8 -> 36.3 | Improved |
| add temporal feature calibration | CrossVIS · OVIS val | AP: 14.9 -> 18.1 | Improved |
| use ResNet-101 instead of ResNet-50 | CrossVIS · YouTube-VIS-2019 val | AP: 34.8 -> 36.6 | Improved |
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.
- STEm-Seg — STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (ECCV 2020) · better on 2 of 2 shared results
- CompFeat — CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation (AAAI 2021) · better on 1 of 1 shared result
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
- In Defense of Online Models for Video Instance Segmentation (ECCV 2022 · similarity 0.90)
- Hybrid Instance-Aware Temporal Fusion for Online Video Instance Segmentation (AAAI 2022 · similarity 0.90)
- InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation (NeurIPS 2022 · similarity 0.90)
- InstanceFormer: An Online Video Instance Segmentation Framework (AAAI 2023 · similarity 0.90)
- SyncVIS: Synchronized Video Instance Segmentation (NeurIPS 2024 · similarity 0.88)
- Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation (AAAI 2025 · similarity 0.87)
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.
