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.

Implementation

The paddlepaddle implementation can be found in [PaddlePaddle].

The pytorch version can be found in [Person_reID_baseline_pytorch].

Citation

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

Related Repos

1. Pedestrian Alignment Network
2. 2stream Person re-ID
3. Pedestrian GAN
4. Language Person Search
5. DG-Net
6. 3D Person re-ID