VALSE 论文速览 第197期：基于ProtoOT的无监督跨域图像检索

论文题目：

Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport

作者列表：

李斌 (上海科技大学)、石野 (上海科技大学)、于茜 (北京航空航天大学）、汪婧雅 (上海科技大学)

B站观看网址：

https://www.bilibili.com/video/BV1tGxKeJETs/?spm_id_from=333.999.0.0&vd_source=2044ac986b5caa4c8b5f00b525441df3

复制链接到浏览器打开或点击阅读原文即可跳转至观看页面。

论文摘要：

Unsupervised cross-domain image retrieval (UCIR) aims to retrieve images sharing the same category across diverse domains without relying on labeled data. Prior approaches have typically decomposed the UCIR problem into two distinct tasks: intra-domain representation learning and cross-domain feature alignment. However, these segregated strategies overlook the potential synergies between these tasks. This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework. ProtoOT leverages the strengths of the K-means clustering method to effectively manage distribution imbalances inherent in UCIR. By utilizing K-means for generating initial prototypes and approximating class marginal distributions, we modify the constraints in Optimal Transport accordingly, significantly enhancing its performance in UCIR scenarios. Furthermore, we incorporate contrastive learning into the ProtoOT framework to further improve representation learning. This encourages local semantic consistency among features with similar semantics, while also explicitly enforcing separation between features and unmatched prototypes, thereby enhancing global discriminativeness. ProtoOT surpasses existing state-of-the-art methods by a notable margin across benchmark datasets. Notably, on DomainNet, ProtoOT achieves an average P@200 enhancement of 24.44%, and on Office-Home, it demonstrates a P@15 improvement of 12.12%. 

参考文献：

[1] Li, B., Shi, Y., Yu, Q., & Wang, J. (2024). Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3009-3017.

论文链接：

[https://arxiv.org/pdf/2402.18411]

代码链接：

[https://github.com/HCVLAB/ProtoOT]

视频讲者简介：

李斌，上海科技大学信息科学与技术学院博士一年级，师从汪婧雅老师。主要研究方向为迁移学习，计算机视觉。

特别鸣谢本次论文速览主要组织者：

月度轮值AC：陈使明 (阿联酋人工智能大学)