Research map / Architectures and efficiency / CNN design
BranchOut: Regularization for Online Ensemble Tracking With Convolutional Neural Networks
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use stochastic BranchOut updates instead of updating all branches deterministically (ablation) | BranchOut tracker · OTB100 | Success (AUC): 0.661 -> 0.678 | Helped |
| select branches randomly instead of selecting them by target scores (ablation) | BranchOut tracker · OTB100 | Success (AUC): 0.658 -> 0.678 | Helped |
| use multi-level branches with one- and two-layer fully connected heads (ablation) | BranchOut tracker · OTB100 | Success (AUC): 0.667 -> 0.678; 0.651 -> 0.678 | Helped |
| apply BranchOut instead of deterministic ensemble updates (ablation) | MDNet ensemble tracker · OTB100 | Success (AUC): 0.674 -> 0.683 | Helped |
| use BranchOut tracking rather than C-COT | OTB100 tracking · OTB100 | Success (AUC): 0.673 -> 0.678 | Helped |
| use BranchOut tracking rather than C-COT | OTB100 tracking · OTB100 | Precision: 0.903 -> 0.917 | Helped |
| use BranchOut rather than TCNN | VOT2015 tracking · VOT2015 | Expected overlap: 0.3404 -> 0.3384 | Hurt |
Closest papers by meaning
- STCT: Sequentially Training Convolutional Networks for Visual Tracking (CVPR 2016 · similarity 0.88)
- Release the Power of Online-Training for Robust Visual Tracking (AAAI 2020 · similarity 0.88)
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (CVPR 2016 · similarity 0.88)
- Target-Aware Deep Tracking (CVPR 2019 · similarity 0.86)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.84)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.83)
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.