GNN-Re-Ranking

Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective

[Paper]

On the Market-1501 dataset, we accelerate the re-ranking processing from 89.2s to 9.4ms with one K40m GPU, facilitating the real-time post-processing. Similarly, we observe that our method achieves comparable or even better retrieval results on the other four image retrieval benchmarks, i.e., VeRi-776, Oxford-5k, Paris-6k and University-1652, with limited time cost.

1. Prerequisites

• CUDA 9
• cuDNN >=7.3
• paddlepaddle-gpu == 1.6.3

To compile it:

cd lib
sh make.sh

2. Demo

The demo script main.py provides the gnn re-ranking method using the prepared feature.

source set_env.sh
python main.py --data_path PATH_TO_DATA --k1 26 --k2 7

3. Citation

@article{zhang2020understanding,
  title={Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective},
  author={Xuanmeng Zhang, Minyue Jiang, Zhedong Zheng, Xiao Tan, Errui Ding, Yi Yang},
  journal={arXiv preprint arXiv:2012.07620},
  year={2020}
}