Central similarity consistency hashing for asymmetric image retrieval  

作　　者：Zhaofeng Xuan Dayan Wu Wanqian Zhang Qinghang Su Bo Li Weiping Wang 

机构地区：[1]Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100085,China [2]School of Cyber Security,University of Chinese Academy of Sciences,Beijing 100049,China [3]Key Laboratory of Cyberspace Security Defense,Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100085,China

出　　处：《Computational Visual Media》2024年第4期725-740,共16页计算可视媒体（英文版）

基　　金：supported by the National Key R&D Program of China under Grant 2022YFB3103500;the National Natural Science Foundation of China under Grants 62106258 and 62202459;the China Postdoctoral Science Foundation under Grant 2022M713348;Young Elite Scientists Sponsorship Program by BAST(BYESS2023304).

摘　　要：Asymmetric image retrieval methods have drawn much attention due to their effectiveness in resource-constrained scenarios.They try to learn two models in an asymmetric paradigm,i.e.,a small model for the query side and a large model for the gallery.However,we empirically find that the mutual training scheme(learning with each other)will inevitably degrade the performance of the large gallery model,due to the negative effects exerted by the small query one.In this paper,we propose Central Similarity Consistency Hashing(CSCH),which simultaneously learns a small query model and a large gallery model in a mutually promoted manner,ensuring both high retrieval accuracy and efficiency on the query side.To achieve this,we first introduce heuristically generated hash centers as the common learning target for both two models.Instead of randomly assigning each hash center to its corresponding category,we introduce the Hungarian algorithm to optimally match each of them by aligning the Hamming similarity of hash centers to the semantic similarity of their classes.Furthermore,we introduce the instance-level consistency loss,which enables the explicit knowledge transfer from the gallery model to the query one,without the sacrifice of gallery performance.Guided by the unified learning of hash centers and the distilled knowledge from gallery model,the query model can be gradually aligned to the Hamming space of the gallery model in a decoupled manner.Extensive experiments demonstrate the superiority of our CSCH method compared with current state-of-the-art deep hashing methods.The open-source code is available at https://github.com/dubanx/CSCH.

关 键 词：asymmetric image retrieval deep hashing Hungarian algorithm decoupled manner 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]