Optimizing Siamese-Based Networks through Multi-Level Mask-Guided Learning in VOT (MML Method)

Examples of SiamBAN outputs. The green boxes are the ground-truth bounding boxes of VOT2018, the yellow boxes are results yielded by SiamBAN.

Installation

Please find installation instructions in INSTALL.md.

Quick Start: Using MML

Add MML to your PYTHONPATH

export PYTHONPATH=/path/to/MML:$PYTHONPATH

Download models

Download models in Model Zoo and put the model.pth in the correct directory in experiments

Webcam demo

python tools/demo.py \
    --config experiments/siamban_r50_l234/config.yaml \
    --snapshot experiments/siamban_r50_l234/model.pth
    # --video demo/bag.avi # (in case you don't have webcam)

Download testing datasets

Download datasets and put them into testing_dataset directory. Jsons of commonly used datasets can be downloaded from here or here, extraction code: 8fju. If you want to test tracker on new dataset, please refer to pysot-toolkit to setting testing_dataset.

Test tracker

cd experiments/siamban_r50_l234
python -u ../../tools/test.py 	\
	--snapshot model.pth 	\ # model path
	--dataset VOT2018 	\ # dataset name
	--config config.yaml	  # config file

The testing results will in the current directory(results/dataset/model_name/)

Eval tracker

assume still in experiments/siamban_r50_l234

python ../../tools/eval.py 	 \
	--tracker_path ./results \ # result path
	--dataset VOT2018        \ # dataset name
	--num 1 		 \ # number thread to eval
	--tracker_prefix 'model'   # tracker_name

Training 🔧

See TRAIN.md for detailed instruction.

Reference

• Siamese Box Adaptive Network for Visual Tracking
• official repo