The official implementation of the ICCV 2023 paper Robust Object Modeling for Visual Tracking
[Models and Raw Results] (Google Drive) [Models and Raw Results] (Baidu Netdisk: romt)
[September 21, 2023]
- We release Models and Raw Results of ROMTrack.
- We refine README for more details.
[August 6, 2023]
- We release Code of ROMTrack.
[July 14, 2023]
- ROMTrack is accepted to ICCV2023.
- Code for ROMTrack
- Model Zoo and Raw Results
- Refine README
- ROMTrack employes a robust object modeling design which can keep the inherent information of the target template and enables mutual feature matching between the target and the search region simultaneously.
Use the Anaconda
conda create -n romtrack python=3.6
conda activate romtrack
bash install_pytorch17.sh
Put the tracking datasets in ./data. It should look like:
${ROMTrack_ROOT}
-- data
-- lasot
|-- airplane
|-- basketball
|-- bear
...
-- lasot_ext
|-- atv
|-- badminton
|-- cosplay
...
-- got10k
|-- test
|-- train
|-- val
-- coco
|-- annotations
|-- train2017
-- trackingnet
|-- TRAIN_0
|-- TRAIN_1
...
|-- TRAIN_11
|-- TEST
Run the following command to set paths for this project
python tracking/create_default_local_file.py --workspace_dir . --data_dir ./data --save_dir .
After running this command, you can also modify paths by editing these two files
lib/train/admin/local.py # paths about training
lib/test/evaluation/local.py # paths about testing
Training with multiple GPUs using DDP. More details of other training settings can be found at tracking/train_romtrack.sh
bash tracking/train_romtrack.sh
- LaSOT/LaSOT_ext/GOT10k-test/TrackingNet/OTB100/UAV123/NFS30. More details of test settings can be found at
tracking/test_romtrack.sh
bash tracking/test_romtrack.sh
python tracking/profile_model.py --config="baseline_stage1"
We provide attention maps and feature maps for several sequences on LaSOT. Detailed analysis can be found in our paper.
- Thanks for STARK, PyTracking and MixFormer Library, which helps us to quickly implement our ideas and test our performances.
- Our implementation of the ViT is modified from the Timm repo.
If our work is useful for your research, please feel free to star:star: and cite our paper:
@article{DBLP:journals/corr/abs-2308-05140,
author = {Yidong Cai and
Jie Liu and
Jie Tang and
Gangshan Wu},
title = {Robust Object Modeling for Visual Tracking},
journal = {CoRR},
volume = {abs/2308.05140},
year = {2023}
}