Research map / Detection and segmentation / CNN features
FairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, 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 |
|---|---|---|---|
| sample re-ID features at object centers instead of ROI-Align (ablation) | FairMOT · MOT17 val | IDF1: 71.0 -> 72.8 | Improved |
| use one-stage center sampling instead of two-stage re-ID (ablation) | FairMOT · MOT17 val | IDF1: 68.2 -> 72.8 | Improved |
| add bi-linear interpolation to center sampling (ablation) | FairMOT · MOT17 val | IDF1 / MOTA: IDF1 72.8 -> 74.3, MOTA 69.1 -> 68.8 | Mixed |
| replace fixed loss weights with uncertainty weighting (ablation) | FairMOT · MOT17 val | IDs / MOTA: IDs 387 -> 299, MOTA 69.6 -> 69.1 | Mixed |
| add multi-layer feature fusion (FPN) to RegNetY-4.0GF (ablation) | FairMOT · MOT17 val | MOTA: 63.9 -> 65.8 | Improved |
| use larger backbone ResNet-50 instead of ResNet-34 (ablation) | FairMOT · MOT17 val | MOTA: 63.6 -> 63.7 | No clear effect |
| add FPN fusion to ResNet-34 (ablation) | FairMOT · MOT17 val | TPR: 90.9 -> 94.2 | Improved |
| keep deformable convolutions in DLA-34 (ablation) | FairMOT · MOT17 val | MOTA: 65.0 -> 69.1 | Improved |
| train the re-ID branch alongside detection (feature conflict) (ablation) | FairMOT ResNet-34 · MOT17 val | AP: 76.1 -> 75.1 | Hurt |
| reduce re-ID feature dimension from 512 to 64 (ablation) | FairMOT · MOT17 val | MOTA: 68.5 -> 69.2 | Improved |
| reduce re-ID feature dimension from 512 to 64 (ablation) | JDE · MOT17 val | MOTA: 59.9 -> 60.3 | Improved |
| add Kalman filter to re-ID association (ablation) | FairMOT DLA-34 · MOT17 val | IDs: 435 -> 342 | Improved |
Later papers that compared with this method
14 later accepted papers report FairMOT as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.
- ProgTrack: A Multi-Object Tracking Algorithm with Progressive Matching Strategy (CVPR 2026 · better on 1 of 1 shared result)
- When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking (AAAI 2026 · better on 1 of 1 shared result)
- Referring Multi-Object Tracking with Diverse Dynamic Expressions (TPAMI 2026 · better on 1 of 1 shared result)
- Delving into the Trajectory Long-tail Distribution for Muti-object Tracking (CVPR 2024 · better on 6 of 9 shared results)
- Referring Multi-Object Tracking (CVPR 2023 · better on 1 of 1 shared result)
- One More Check: Making “Fake Background” Be Tracked Again (AAAI 2022 · better on 6 of 6 shared results)
- MeMOT: Multi-Object Tracking With Memory (CVPR 2022 · better on 1 of 3 shared results)
- Few-Shot Video Object Detection (ECCV 2022 · better on 3 of 3 shared results)
6 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TubeTK — TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model (CVPR 2020) · better on 2 of 2 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
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.89)
- DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion (CVPR 2022 · similarity 0.88)
- One More Check: Making “Fake Background” Be Tracked Again (AAAI 2022 · similarity 0.87)
- Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking (CVPR 2019 · similarity 0.87)
- SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation (AAAI 2026 · similarity 0.86)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 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.
