Discriminative and Robust Online Learning for Siamese Visual Tracking (AAAI 2020)
This is the repo for paper "Discriminative and Robust Online Learning for Siamese Visual Tracking" [paper] [results], presented as poster at AAAI 2020.
The proposed Discriminative and Robust Online Learning (DROL) module is designed to work with a variety of off-the-shelf siamese trackers. Our method is extensively evaluated over serveral mainstream benchmarks and is believed to induce a consistant performance gain over the given baseline. The model includes but not limited to, as paper evaluated:
The corresponding offline-trained models are availabe at PySOT Model Zoo.
INSTALL.md
.export PYTHONPATH=/path/to/drol:$PYTHONPATH
Download models in PySOT Model Zoo and put the model.pth to the corresponding directory in experiment.
cd experiments/siamrpn_r50_l234_dwxcorr
python -u ../../tools/test.py \
--snapshot model.pth \ # model path
--dataset VOT2018 \ # dataset name
--config config.yaml # config file
assume still in experiments/siamrpn_r50_l234_dwxcorr_8gpu
python ../../tools/eval.py \
--tracker_path ./results \ # result path
--dataset VOT2018 \ # dataset name
--num 1 \ # number thread to eval
--tracker_prefix 'model' # tracker_name
For DROL-RPN
, we have seperate config file thus each own experiment file folder for vot
/votlt
/otb
/others
, where vot
is used for VOT-20XX-baseline
benchmark, votlt
for VOT-20XX-longterm
benchmark, otb
for OTB2013/15
benchmark, and others
is default setting thus for all the other benchmarks, including but not limited to LaSOT
/TrackingNet
/UAV123
.
For DROL-FC/DROL-Mask
, only experiments on vot/otb
are evaluated as described in the paper. Similar to the repo of PySOT
, we use config file for vot
as default setting.
Since this repo is a grown-up modification of PySOT, we recommend to refer to PySOT for more technical issues.