Architecture

Usage

Installation:

1. Create the environment from the environment.yml file:

    conda env create -f environment.yml
   

2. Activate the new environment:

    conda activate bmvc
   

3. Verify that the new environment was installed correctly:

    conda env list
   

You can also use conda info --envs.

Configuration:

1. Reset the correct path of the data sets in dataer.py.

2. Reset the model in models.py and init it in main.py.

3. Ensure all the hyparameters is what you need and then:

    python main.py
   

You can also use command like this:

python main.py -c <cuda.id> -e <epoch> -b <batch_size> -d <dataset> -fp <save_dir> -nn <model_name> -lr <learning_rate>

Results

Revision

In Table1, Table2: KLCC -> KRCC
In Table1: 0.9376 -> 0.8376

Citation

@inproceedings{Wang_2022_BMVC,
    author    = {Weibo Wang and Xinghui Dong},
    title     = {Unifying the Visual Perception of Humans and Machines on Fine-Grained Texture Similarity},
    booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
    publisher = {{BMVA} Press},
    year      = {2022},
    url       = {https://bmvc2022.mpi-inf.mpg.de/0839.pdf}
}