Bag of Tricks for Domain Adaptive Multi-Object Tracking
Not on the map. Why?
Abstract (arXiv)
In this paper, SIA_Track is presented which is developed by a research team from SI Analytics. The proposed method was built from pre-existing detector and tracker under the tracking-by-detection paradigm. The tracker we used is an online tracker that merely links newly received detections with existing tracks. The core part of our method is training procedure of the object detector where synthetic and unlabeled real data were only used for training. To maximize the performance on real data, we first propose to use pseudo-labeling that generates imperfect labels for real data using a model trained with synthetic dataset. After that model soups scheme was applied to aggregate weights produced during iterative pseudo-labeling. Besides, cross-domain mixed sampling also helped to increase detection performance on real data. Our method, SIA_Track, takes the first place on MOTSynth2MOT17 track at BMTT 2022 challenge. The code is available on https://github.com/SIAnalytics/BMTT2022_SIA_track.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 23 references that are in the map. First posted on arXiv 31 May 2022.
Builds on
22 of 23 references.
References · 22
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2018CBAM: Convolutional Block Attention Modulecited by 2,477
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
- 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
- 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
- 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
- 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 692
- 2021Domain Generalization with MixStylecited by 566
- 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 552
- 2016MOT16: A Benchmark for Multi-Object Trackingcited by 532
- 2020Tracking Objects as Pointscited by 483
- 2019Tracking without bells and whistlescited by 382
10 more
- 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
- 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
- 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
- 2022StrongSORT: Make DeepSORT Great Againcited by 213
- 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
- 2019A Robust Learning Approach to Domain Adaptive Object Detectioncited by 109
- 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 69
- 2019Automatic adaptation of object detectors to new domains using self-trainingcited by 66
- 2020Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detectioncited by 44
- 2019Reducing Domain Gap by Reducing Style Biascited by 35
Built on by
Citing papers per year: 2022: 1.
1 paper.