• Finding Visual Saliency in Continuous Spike Stream is accepted by AAAI 2024!

• Recurrent Spiking Transformers for Saliency Detection in Continuous Integration-based Visual Streams is under review.

• Journal version：Recurrent Spiking Transformers for Saliency Detection in Continuous Integration-based Visual Streams.
• Code for journal version will be available soon!

• torch >= 1.8.0
• torchvison >= 0.9.0
• ...

To installl requirements, run:

conda create -n svs python==3.7
pip install -r requirements.txt

Download the SVS[3tqk] dataset, then organize data as following format:

root_dir
    SpikeData
        |----00001
        |     |-----spike_label_format
        |     |-----spike_numpy
        |     |-----spike_repr
        |     |-----label
        |----00002
        |     |-----spike_label_format
        |     |-----spike_numpy
        |     |-----spike_repr
        |     |-----label
        |----...

Where label contains the saliency labels, spike_numpy contains the compress spike data, spike_repr contains the interval spike representation, spike_label_format contains instance labels.

To train the model on SVS dataset, just modify the dataset root $cfg.DATA.ROOT in config.py, --step is used for multi-step, --clip is used for multi-step loss, then run following command:

python train.py --gpu ${GPU-IDS} --exp_name ${experiment} --step --clip

Download the model pretrained on SVS dataset multi_step[vn2x].

python inference.py --checkpoint ${./multi_step.pth} --results ${./results/SVS} --step

Download the model pretrained on SVS dataset single_step[scc0].

python inference.py --checkpoint ${./single_step.pth} --results ${./results/SVS}

The results will be saved as indexed png file at ${results}/SVS.

Additionally, you can modify some setting parameters in config.py to change configuration.

This codebase is built upon official DCFNet repository and official Spikformer repository. We modify the code from eval-co-sod to evaluate the results.