Paper: Outfit Compatibility Prediction and Diagnosis with Multi-Layered Comparison Network
by Xin Wang, Bo Wu, Yueqi Zhong. Published at ACM MM 2019 in Nice, France.
Ubuntu 16.04, NVIDIA GTX 1080Ti (for batch size 16), python >= 3.5.2
torch==1.0.1
torchvision==0.2.1
networkx==2.4
opencv-python==4.2.0.32
matplotlib==2.2.2
scikit-learn==0.21.2
Download the original Polyvore dataset, then unzip the file and put the image
directory into data
folders (or you can create a soft link for it).
Train
cd mcn
python train.py
Evaluate
python evaluate.py
Visualize outfit diagnosis
cd exp
python diagnosis.py
Automatically revise outfit
python revision.py
Pretrained model weights can be found in the links. The train, validation and test split is provided in data.
AUC | FITB | |
---|---|---|
Pooling | 88.35 | 57.28 |
Concatenation | 83.40 | 52.91 |
Self-attention | 79.65 | 48.60 |
BiLSTM | 74.82 | 46.02 |
CSN | 84.90 | 57.06 |
Ours | 91.90 | 64.35 |
A demo application is in the app directioy. You can run it locally by go to app directory then use command python main.py
.
More guide can be found in here.
Please cite our paper if you use or refer this code:
@inproceedings{wang2019diagnosis,
title={Outfit Compatibility Prediction and Diagnosis with Multi-Layered Comparison Network},
author={Xin Wang, Bo Wu and Yueqi Zhong},
booktitle={ACM International Conference on Multimedia},
year={2019}
}