Research map / Detection and segmentation / Tracking
Heterogeneous Diversity Driven Active Learning for Multi-Object Tracking
Rui Li, Baopeng Zhang, Jun Liu, Wei Liu, Jian Zhao, Zhu Teng
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 multi-frame cooperation to IFSN (ablation) | HD-AMOT · MOT17 (20% budget) | MOTA / IDF1: MOTA 62.76 -> 63.23, IDF1 65.52 -> 66.47 | Improved |
| use cluster-based batch sampling instead of top-N score batch sampling (ablation) | HD-AMOT · MOT17 (20% budget) | MOTA / IDF1: MOTA 62.18 -> 63.23, IDF1 64.55 -> 66.47 | Improved |
| batch sampling instead of one frame per iteration (ablation) | HD-AMOT · MOT17 (20% budget) | MOTA / IDF1: MOTA 63.07 -> 63.23, IDF1 65.62 -> 66.47 | Improved |
| add novelty histograms to action representation (ablation) | HD-AMOT · MOT17 (20% budget) | MOTA / IDF1: MOTA 61.25 -> 63.23, IDF1 63.41 -> 66.47 | Improved |
| add geometric topology to state (ablation) | HD-AMOT · MOT17 (20% budget) | MOTA: 61.73 -> 63.23 | Improved |
| add geometric scale/topology histogram HGh to action (ablation) | HD-AMOT · MOT17 (20% budget) | IDF1: 66.61 (without) vs 66.47 (full) | No clear effect |
| use HD-AMOT sampling instead of uniform sampling | FairMOT · MOT17 test | IDF1: MOTA 70.40 -> 71.24, IDF1 70.05 -> 69.87 | Mixed |
| use HD-AMOT instead of random sampling | FairMOT · MOT20 test | MOTA: 58.21 -> 59.24 | Improved |
| apply Coreset/CDAL image-level active learning directly to MOT | FairMOT · MOT20 test | MOTA: Random 58.21 -> Coreset 56.66 | Hurt |
| train with 50% actively selected labels instead of full supervision | FairMOT · MOT15 | MOTA: gain of 2% MOTA and 0.8% IDF1 | Improved |
Closest papers by meaning
- Towards Frame Rate Agnostic Multi-object Tracking (IJCV 2023 · similarity 0.87)
- Sampling-Resilient Multi-Object Tracking (AAAI 2024 · similarity 0.87)
- GMOT-40: A Benchmark for Generic Multiple Object Tracking (CVPR 2021 · similarity 0.87)
- Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking (AAAI 2024 · similarity 0.87)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.86)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.85)
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.
