Research map / Label-efficient and robust learning / Semi-supervised learning
Optical Flow Training under Limited Label Budget via Active Learning
Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, Carlo Tomasi
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 20% labels (semi-supervised) to unsupervised ARFlow | ARFlow · Sintel final val | EPE: 2.933 -> 2.598 | Improved |
| add 5% labels to unsupervised training | ARFlow · FlyingChairs val | EPE: 3.066 -> 2.369 | Improved |
| select labels by occ ratio instead of random | Semi-sup ARFlow r=0.1 · Sintel final val | EPE: 2.710 -> 2.515 | Improved |
| select labels by flow grad norm instead of random | Semi-sup ARFlow r=0.2 · Sintel final val | EPE: 2.598 -> 2.299 | Improved |
| select labels by photo loss instead of random | Semi-sup ARFlow r=0.2 · Sintel final val | EPE: 2.598 -> 2.383 | Improved |
| select labels by occ ratio instead of random | Semi-sup ARFlow r=0.05 · KITTI 2012 val | Fl: 5.363 | Improved |
| add unlabeled samples of train split to Stage 2 (semi-sup vs sup only) (ablation) | Occ ratio AL r=0.1 · Sintel final val | EPE: 2.59 -> 2.52 | Improved |
| avoid adding raw Stage-1 unlabeled data to Stage 2 (ablation) | Random sampling r=0.1 · Sintel final val | EPE: 3.13 -> 2.71 | Improved |
| use occ-2x (sample half of top-2x uncertain) instead of occ | Semi-sup ARFlow r=0.2 · Sintel test final | EPE: 5.09 -> 4.62 | Improved |
| use occ ratio instead of random | Semi-sup ARFlow r=0.1 · Sintel test clean | EPE: 3.91 -> 4.28 | Hurt |
| use occ ratio instead of random | Semi-sup ARFlow r=0.1 · KITTI-2015 test | Fl-all: 9.51 -> 8.96 | Improved |
| use occ ratio instead of random | Semi-sup ARFlow r=0.2 · KITTI-2015 test | Fl-all: 8.38 -> 8.30 | No clear effect |
Closest papers by meaning
- Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks (NeurIPS 2017 · similarity 0.90)
- Semi-Supervised Learning of Optical Flow by Flow Supervisor (ECCV 2022 · similarity 0.90)
- Learning by Analogy: Reliable Supervision From Transformations for Unsupervised Optical Flow Estimation (CVPR 2020 · similarity 0.88)
- ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF (CVPR 2024 · similarity 0.87)
- Recurrent Partial Kernel Network for Efficient Optical Flow Estimation (AAAI 2024 · similarity 0.87)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (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.
