tsbir / README.md
Patsorn
update README.md
fbfe339
|
raw
history blame
1.88 kB

Image Retrieval with Text and Sketch

This code is for our 2022 ECCV paper [A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch]


folder structure

|---model/       : Contain the trained model*
|---sketches/    : Contain example query sketch
|---images/      : Contain 100 randomly sampled images from COCO TBIR benchmark
|---notebooks/   : Contain the demo ipynb notebook (can run via Colab)
|---code/        
    |---training/model_configs/      : Contain model config file for the network
    |---clip/                        : Contain source code for running the notebook    

*model can be downloaded from https://patsorn.me/projects/tsbir/data/tsbir_model_final.pt

This repo is based on open_clip implementation from https://github.com/mlfoundations/open_clip

Prerequisites

  • Pytorch

Getting Started

Simply run notebooks/Retrieval_Demo.ipynb, you can use your own set of images and sketches by modifying the images/ and sketches/ folder accordingly.

Download Models

Pre-trained models

Citation

If you find it this code useful for your research, please cite:

"A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch"

Patsorn Sangkloy, Wittawat Jitkrittum, Diyi Yang, James Hays in ECCV, 2022.

@article{
 tsbir2022,
 author = {Patsorn Sangkloy and Wittawat Jitkrittum and Diyi Yang and James Hays},
 title = {A Sketch is Worth a Thousand Words: Image Retrieval with Text and Sketch},
 journal = {European Conference on Computer Vision, ECCV},
 year = {2022},
}