Research map / Video / Video segmentation and tracking
AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation
Huaijia Lin, Xiaojuan Qi, 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 instance-specific module (ablation) | AGSS-VOS · Youtube-VOS val | G overall (%): 67.0 -> 71.3 | Improved |
| add the instance-agnostic module (ablation) | AGSS-VOS · Youtube-VOS val | G overall (%): 58.6 -> 71.3 | Improved |
| add probabilistic normalization (ablation) | AGSS-VOS · Youtube-VOS val | G overall (%): 68.6 -> 71.3 | Improved |
| add optical flow alignment of the previous mask (ablation) | AGSS-VOS · Youtube-VOS val | G overall (%): 67.8 -> 71.3 | Improved |
| pre-train on Youtube-VOS before fine-tuning on DAVIS | AGSS-VOS · DAVIS-2017 val | J&F: 66.6 -> 67.4 | Improved |
| pre-train on Youtube-VOS before fine-tuning on DAVIS | AGSS-VOS · DAVIS-2017 test-dev | J&F: 54.3 -> 57.2 | Improved |
| single-pass multi-object segmentation instead of per-object RGMP | RGMP · Youtube-VOS val | time per frame (s): 0.08 | Improved |
Later papers that compared with this method
2 later accepted papers report AGSS-VOS as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Exploring the Semi-Supervised Video Object Segmentation Problem from a Cyclic Perspective (IJCV 2022 · better on 2 of 2 shared results)
- Learning What to Learn for Video Object Segmentation (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
- Make One-Shot Video Object Segmentation Efficient Again (NeurIPS 2020 · similarity 0.89)
- Learning What to Learn for Video Object Segmentation (ECCV 2020 · similarity 0.89)
- Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation (ECCV 2024 · similarity 0.88)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.88)
- Dual Prototype Attention for Unsupervised Video Object Segmentation (CVPR 2024 · similarity 0.86)
- Putting the Object Back into Video Object Segmentation (CVPR 2024 · similarity 0.86)
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.
