PieTrack: An MOT solution based on synthetic data training and self-supervised domain adaptation

• URL: http://arxiv.org/abs/2207.11325v1
• Date: Fri, 22 Jul 2022 20:34:49 GMT
• Title: PieTrack: An MOT solution based on synthetic data training and self-supervised domain adaptation
• Authors: Yirui Wang, Shenghua He, Youbao Tang, Jingyu Chen, Honghao Zhou, Sanliang Hong, Junjie Liang, Yanxin Huang, Ning Zhang, Ruei-Sung Lin, Mei Han
• Abstract summary: PieTrack is developed based on synthetic data without using any pre-trained weights. By leveraging the proposed multi-scale ensemble inference, we achieved a final HOTA score of 58.7 on the MOT17 testing set, ranked third place in the challenge.
• Score: 17.716808322509667
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In order to cope with the increasing demand for labeling data and privacy issues with human detection, synthetic data has been used as a substitute and showing promising results in human detection and tracking tasks. We participate in the 7th Workshop on Benchmarking Multi-Target Tracking (BMTT), themed on "How Far Can Synthetic Data Take us"? Our solution, PieTrack, is developed based on synthetic data without using any pre-trained weights. We propose a self-supervised domain adaptation method that enables mitigating the domain shift issue between the synthetic (e.g., MOTSynth) and real data (e.g., MOT17) without involving extra human labels. By leveraging the proposed multi-scale ensemble inference, we achieved a final HOTA score of 58.7 on the MOT17 testing set, ranked third place in the challenge.

Related papers

• Learning Human Action Recognition Representations Without Real Humans [66.61527869763819]
  We present a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model. We then evaluate the transferability of the representation learned on this data to a diverse set of downstream action recognition benchmarks. Our approach outperforms previous baselines by up to 5%.
  arXiv  Detail & Related papers  (2023-11-10T18:38:14Z)
• TarGEN: Targeted Data Generation with Large Language Models [51.87504111286201]
  TarGEN is a multi-step prompting strategy for generating high-quality synthetic datasets. We augment TarGEN with a method known as self-correction empowering LLMs to rectify inaccurately labeled instances. A comprehensive analysis of the synthetic dataset compared to the original dataset reveals similar or higher levels of dataset complexity and diversity.
  arXiv  Detail & Related papers  (2023-10-27T03:32:17Z)
• ParGANDA: Making Synthetic Pedestrians A Reality For Object Detection [2.7648976108201815]
  We propose to use a Generative Adversarial Network (GAN) to close the gap between the real and synthetic data. Our approach not only produces visually plausible samples but also does not require any labels of the real domain.
  arXiv  Detail & Related papers  (2023-07-21T05:26:32Z)
• UTOPIA: Unconstrained Tracking Objects without Preliminary Examination via Cross-Domain Adaptation [26.293108793029297]
  Multiple Object Tracking (MOT) aims to find bounding boxes and identities of targeted objects in consecutive video frames. fully-supervised MOT methods have achieved high accuracy on existing datasets, but cannot generalize well on a newly obtained dataset or a new unseen domain. In this work, we first address the MOT problem from the cross-domain point of view, imitating the process of new data acquisition in practice. A new cross-domain MOT adaptation from existing datasets is proposed without any pre-defined human knowledge in understanding and modeling objects.
  arXiv  Detail & Related papers  (2023-06-16T04:06:15Z)
• SDTracker: Synthetic Data Based Multi-Object Tracking [8.43201092674197]
  We present SDTracker, a method that harnesses the potential of synthetic data for multi-object tracking of real-world scenes. We use the ImageNet dataset as an auxiliary to randomize the style of synthetic data. We also adopt the pseudo-labeling method to effectively utilize the unlabeled MOT17 training data.
  arXiv  Detail & Related papers  (2023-03-26T08:21:22Z)
• ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization [65.58562481279023]
  We propose ZooD, a paradigm for PTMs ranking and ensemble with feature selection. We evaluate our paradigm on a diverse model zoo consisting of 35 models for various Out-of-Distribution (OoD) tasks.
  arXiv  Detail & Related papers  (2022-10-17T16:31:57Z)
• GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation [60.07812405063708]
  3D point cloud semantic segmentation is fundamental for autonomous driving. Most approaches in the literature neglect an important aspect, i.e., how to deal with domain shift when handling dynamic scenes. This paper advances the state of the art in this research field.
  arXiv  Detail & Related papers  (2022-07-20T09:06:07Z)
• Bag of Tricks for Domain Adaptive Multi-Object Tracking [4.084199842578325]
  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. Our method, SIA_Track, takes the first place on MOT Synth2MOT17 track at BMTT 2022 challenge.
  arXiv  Detail & Related papers  (2022-05-31T08:49:20Z)
• MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking? [36.094861549144426]
  Deep learning methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance. We generate MOT Synth, a large, highly diverse synthetic dataset for object detection and tracking using a rendering game engine. Our experiments show that MOT Synth can be used as a replacement for real data on tasks such as pedestrian detection, re-identification, segmentation, and tracking.
  arXiv  Detail & Related papers  (2021-08-21T14:25:25Z)
• From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation [67.39635503744395]
  Animal pose estimation is an important field that has received increasing attention in the recent years. Existing works circumvent this problem with pseudo labels generated from data of other easily accessible domains such as synthetic data. We design a multi-scale domain adaptation module (MDAM) to reduce the domain gap between the synthetic and real data. Specifically, we propose a self-distillation module in an inner coarse-update loop and a mean-teacher in an outer fine-update loop to generate new pseudo labels that gradually replace the old ones.
  arXiv  Detail & Related papers  (2021-03-27T08:39:43Z)
• UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification [102.58619642363959]
  This paper presents UnrealPerson, a novel pipeline that makes full use of unreal image data to decrease the costs in both the training and deployment stages. With 3,000 IDs and 120,000 instances, our method achieves a 38.5% rank-1 accuracy when being directly transferred to MSMT17.
  arXiv  Detail & Related papers  (2020-12-08T08:15:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.