D3still : Decoupled differential distillation for asymmetric image retrieval

• Main Authors: XIE, Yi, LIN, Yihong, CAI, Wenjie, XU, Xuemiao, ZHANG, Huaidong, DU, Yong, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Asymmetric image retrieval; Decoupled differential distillation framework; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/9776; https://ink.library.smu.edu.sg/context/sis_research/article/10776/viewcontent/Xie_D3still_CVPR_2024_paper.pdf
• Institution: Singapore Management University

Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint between the query network and the larger gallery network. However, these oneto-one constraint approaches often fail to maintain retrieval order consistency, especially when the query network has limited representational capacity. To overcome this problem, we introduce the Decoupled Differential Distillation (D3still) framework. This framework shifts from absolute one-to-one supervision to optimizing the relational differences in pairwise similarities produced by the query and gallery networks, thereby preserving a consistent retrieval order across both networks. Our method involves computing a pairwise similarity differential matrix within the gallery domain, which is then decomposed into three components: feature representation knowledge, inconsistent pairwise similarity differential knowledge, and consistent pairwise similarity differential knowledge. This strategic decomposition aligns the retrieval ranking of the query network with the gallery network effectively. Extensive experiments on various benchmark datasets reveal that D3still surpasses state-of-the-art methods in asymmetric image retrieval.