ltp1995/GCAGC-CVPR2020

Co-saliency detection, GCAGC, CVPR2020, GCAGC-Inst, TMM2021. Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection

Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection (GCAGC-CVPR2020)

Pipeline

Testing code

• python test.py

Pretrained models (HRNET version)

• Baidu Cloud Fetchcode: isrw && Google Cloud

Training Dataset (COCO-SEG, 78 categories, 200K images) && Cosal results

• Baidu Cloud Fetchcode: rbbj
• Baidu Cloud Fetchcode: aqaw && Google Cloud

Instance co-segmentation and co-saliency (published in TMM)

• Here is our extended transaction paper https://ieeexplore.ieee.org/abstract/document/9337219/
• Instance co-saliency/segmentation maps: Baidu Cloud Fetchcodes: 05em
• Instance evaluation codes (Matlab): Baidu Cloud Fetchcodes: v1up
• Google Cloud: link

Citation

If you use this code, please cite our paper:

@inproceedings{zhang2020adaptive,
  title={Adaptive graph convolutional network with attention graph clustering for co-saliency detection},
  author={Zhang, Kaihua and Li, Tengpeng and Shen, Shiwen and Liu, Bo and Chen, Jin and Liu, Qingshan},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={9050--9059},
  year={2020}
}
@article{li2021image,
  title={Image Co-saliency Detection and Instance Co-segmentation using Attention Graph Clustering based Graph Convolutional Network},
  author={Li, Tengpeng and Zhang, Kaihua and Shen, Shiwen and Liu, Bo and Liu, Qingshan and Li, Zhu},
  journal={IEEE Transactions on Multimedia},
  year={2021},
  publisher={IEEE}
}