A Novel Approach to Incremental Diffusion for Continuous Dataset Updates in Image Retrieval
Source abstract
Abstract
Diffusion is well known for its success in improving retrieval performance by exploiting the local structure of data distribution. Some recent works have focused on improving its efficiency by shifting the computing burden offline. However, we find that efficient offline diffusion handles continuously updating datasets with difficulty, which directly hinders its application in the real world. Unlike previous methods that apply diffusion to the entire gallery, we introduce an anchor graph to serve as an agent of the complete gallery graph. By doing that, we empower diffusion with the ability of retrieving newly added images at acceptable computational cost. We demonstrate that our proposed method is a good approximation of diffusion featuring fast online search speed and the ability of handling growing data. Moreover, experiments on benchmark datasets show that the proposed method outperforms the state of the art by a large margin with proper parameter settings.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image and Video Retrieval Techniques · Image Retrieval and Classification Techniques · Advanced Data Compression Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Funding
National Natural Science Foundation of China
References (31)
Show source-provided references
1. Deep learning for instance retrieval: A survey10.1109/TPAMI.2022.3218591 ↗
2. Donoser, M., and Bischof, H. (2013, January 23–28). Diffusion processes for retrieval revisited. Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.174 ↗
3. Multi-View Diffusion Process for Spectral Clustering and Image Retrieval10.1109/TIP.2023.3302517 ↗
4. Iscen, A., Tolias, G., Avrithis, Y., Furon, T., and Chum, O. (2017, January 21–26). Efficient diffusion on region manifolds: Recovering small objects with compact cnn representations. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.105 ↗
5. Yang, F., Hinami, R., Matsui, Y., Ly, S., and Satoh, S. (February, January 27). Efficient image retrieval via decoupling diffusion into online and offline processing. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, Hi, USA.
6. A dataset and benchmark for multimodal biometric recognition based on fingerprint and finger vein10.1109/TIFS.2022.3175599 ↗
7. The recognition of fingerprints on mobile applications—An android case study
8. Deep face recognition: A survey10.1016/j.neucom.2020.10.081 ↗
9. Graph convolutional network hashing10.1109/TCYB.2018.2883970 ↗
10. Revaud, J., Almazán, J., Rezende, R.S., and de Souza, C.R. (November, January 27). Learning with average precision: Training image retrieval with a listwise loss. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00521 ↗
11. End-to-end learning of deep visual representations for image retrieval10.1007/s11263-017-1016-8 ↗
12. Radenović, F., Tolias, G., and Chum, O. (2016, January 11–14). CNN image retrieval learns from BoW: Unsupervised fine-tuning with hard examples. Proceedings of the Computer Vision—ECCV 2016, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_1 ↗
13. Chum, O., Philbin, J., Sivic, J., Isard, M., and Zisserman, A. (2007, January 14–21). Total recall: Automatic query expansion with a generative feature model for object retrieval. Proceedings of the 2007 IEEE 11th International Conference on Computer Vision, Rio de Janeiro, Brazil.10.1109/ICCV.2007.4408891 ↗
14. Page, L., Brin, S., Motwani, R., and Winograd, T. (1999). The PageRank Citation Ranking: Bringing Order to the Web, Stanford InfoLab. Technical Report.
15. Zhou, D., Weston, J., Gretton, A., Bousquet, O., and Schölkopf, B. (2003, January 9–11). Ranking on data manifolds. Proceedings of the 17th International Conference on Neural Information Processing Systems, Whistler, BC, Canada.
16. Bai, S., Bai, X., Tian, Q., and Latecki, L.J. (2017, January 4–9). Regularized diffusion process for visual retrieval. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), San Francisco, CA, USA.10.1609/aaai.v31i1.11216 ↗
17. Liu, W., He, J., and Chang, S.F. (2010, January 21–24). Large graph construction for scalable semi-supervised learning. Proceedings of the 27th International Conference on International Conference on Machine Learning, St. Madison, WI, USA.
18. Nonlinear dimensionality reduction by locally linear embedding10.1126/science.290.5500.2323 ↗
19. CGD: Multi-View Clustering via Cross-View Graph Diffusion
20. Zhou, D., Bousquet, O., Lal, T., Weston, J., and Schölkopf, B. (2003, January 9–11). Learning with local and global consistency. Proceedings of the 17th International Conference on Neural Information Processing Systems, Cambridge, MA, USA.
21. Yang, C., Tang, J., Sun, M., Cui, G., and Liu, Z. (2019, January 10–16). Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), Macao, China.10.24963/ijcai.2019/560 ↗
22. Yang, F., Wang, Z., Xiao, J., and Satoh, S. (2020, January 7–12). Mining on Heterogeneous Manifolds for Zero-Shot Cross-Modal Image Retrieval. Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), New York, NY, USA.
23. Johnson, J., Douze, M., and Jégou, H. (2017). Billion-scale similarity search with GPUs. arXiv.
24. Philbin, J., Chum, O., Isard, M., Sivic, J., and Zisserman, A. (2007, January 17–22). Object retrieval with large vocabularies and fast spatial matching. Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.10.1109/CVPR.2007.383172 ↗
25. Philbin, J., Chum, O., Isard, M., Sivic, J., and Zisserman, A. (2008, January 23–28). Lost in quantization: Improving particular object retrieval in large scale image databases. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.10.1109/CVPR.2008.4587635 ↗
26. Radenović, F., Iscen, A., Tolias, G., Avrithis, Y., and Chum, O. (2018, January 18–23). Revisiting oxford and paris: Large-scale image retrieval benchmarking. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00598 ↗
27. Tolias, G., Sicre, R., and Jégou, H. (2015, January 7–9). Particular object retrieval with integral max-pooling of CNN activations. Proceedings of the International Conference on Learning Representations 2015, San Diego, CA, USA.
28. Fine-tuning CNN image retrieval with no human annotation
29. Jégou, H., and Chum, O. (2012, January 7–13). Negative evidences and co-occurences in image retrieval: The benefit of PCA and whitening. Proceedings of the Computer Vision—ECCV 2012, 12th European Conference on Computer Vision, Florence, Italy.10.1007/978-3-642-33709-3_55 ↗
30. Scalable semi-supervised learning by efficient anchor graph regularization10.1109/TKDE.2016.2535367 ↗
31. Arandjelović, R., and Zisserman, A. (2012, January 16–21). Three things everyone should know to improve object retrieval. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.10.1109/CVPR.2012.6248018 ↗