Thanks to visit codestin.com
Credit goes to github.com

Skip to content
/ UniQ Public

This repository is the code for our paper on ACM MM 2024 " UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation"

License

Notifications You must be signed in to change notification settings

Lil-Shake/UniQ

Repository files navigation

UniQ

This is the code for our paper on ACM MM 2024 " UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation"

Installation

  • Create a conda environment

    conda create -n UniQ python==3.8.5
    
  • Activate the environment

    conda activate UniQ
    
  • Install packages

    h5py==3.10.0
    imantics==0.1.12
    easydict==1.11
    scikit-learn==1.3.2
    scipy==1.10.1
    pandas==2.0.3
    detectron2==0.6
    torch==2.2.0+cu118
    torchvision==0.17.0+cu118
    

Dataset

We adopt a subset of Visual Genome VG150 that contains the most frequent 150 object classes and 50 predicate classes.

dataset/
└── vg/
	├── VG_100K/
	├── image_data.json
	├── VG-SGG-dicts-with-attri.json
	└── VG-SGG-with-attri.h5

Training

  • Train unbiased UniQ (with $\alpha = 0.07$, $\beta = 0.75$). Train unbiased UniQ with more number of query groups by setting MODEL.DETR.GROUP_DETR to a costumed number.

    bash train_UniQ.sh
    
  • STS, STT, TST baselines can be trained with their corresponding config files in configs/ .

Evaluation

  • Evaluate unbiased UniQ

    bash test_UniQ.sh
    
  • Evaluate unbiased UniQ with top-k links by setting MODEL.DETR.MATCHER_TOPK 3

Visualization

vis_00

Citation

@inproceedings{10.1145/3664647.3681542,
    title = {UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation},
    author = {Liao Xinyao and Wei Wei and Chen Dangyang and Fu Yuanyuan},
    booktitle = {Proceedings of the 32nd ACM International Conference on Multimedia},
    pages = {8815–8824},
    year = {2024}
}

Acknowledgment

  • This repository is built upon the Iterative Scene Graph Generation developed by Siddhesh Khandelwal and Leonid Sigal. Thanks for their extraordinary contribution to this field.
  • This repository also extended DETR and Group DETR to SGG.

About

This repository is the code for our paper on ACM MM 2024 " UniQ: Unified Decoder with Task-specific Queries for Efficient Scene Graph Generation"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published