Self-Distillation Dual-Memory Online Hashing with Hash Centers for Streaming Data Retrieval

The overall framework of SDOH-HC. The pink region illustrates hash codes learning step while the beige region represents hash function learning step. Within hash codes learning, mistyrose and lightcyan areas are hash centers self-distillation and exemplar memory, respectively.

With the continuous generation of massive amounts of multimedia data nowadays, hashing has demonstrated significant potentials for large-scale search. To handle the emerging needs for streaming data retrieval, online hashing is drawing more and more attention. For online scenario, data distribution may change and concept drifts may occur as new data is continuously added to the database. Inevitably, hashing models may lose or disrupt the previously obtained knowledge when learning from new information, which is called the problem of catastrophic forgetting. In this paper, we propose a new online hashing method called Self-distillation Dualmemory Online Hashing with Hash Centers, which is abbreviated to SDOH-HC, to overcome this challenge. Specifically, SDOH-HC contains replay and distillation modules. For replay, a dual-memory mechanism is proposed which involves hash centers and exemplars. For knowledge distillation, we let hash centers distill information from themselves, i.e., the version of last round. Additionally, a new objective function is further built on above modules and is solved discretely to learn hash codes. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our method.

Self-Distillation Dual-Memory Online Hashing with Hash Centers for Streaming Data Retrieval

Abstract

Qualitative results

Scene Flow Estimation

Motion Segmentation

Citation

Acknowledgments