Výsledky vyhledávání

Report

Test-time Adaptation for Cross-modal Retrieval with Query Shift

Autor: Li, Haobin, Hu, Peng, Zhang, Qianjun, Peng, Xi, Liu, Xiting, Yang, Mouxing

The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such an assumption is easily violated in real-world scenarios due to the co

Externí odkaz: http://arxiv.org/abs/2410.15624

Zobrazit plný text záznamu

Report

A Survey on Deep Clustering: From the Prior Perspective

Autor: Lu, Yiding, Li, Haobin, Li, Yunfan, Lin, Yijie, Peng, Xi

Facilitated by the powerful feature extraction ability of neural networks, deep clustering has achieved great success in analyzing high-dimensional and complex real-world data. The performance of deep clustering methods is affected by various factors

Externí odkaz: http://arxiv.org/abs/2406.19602

Zobrazit plný text záznamu

Report

General Procedure to Provide High-Probability Guarantees for Stochastic Saddle Point Problems

Autor: Li, Dongyang, Li, Haobin, Zhang, Junyu

Publikováno v: Journal of Scientific Computing 100 (2024) 13

This paper considers smooth strongly convex and strongly concave (SC-SC) stochastic saddle point (SSP) problems. Suppose there is an arbitrary oracle that in expectation returns an $\epsilon$-solution in the sense of certain gaps, which can be the du

Externí odkaz: http://arxiv.org/abs/2405.03219

Zobrazit plný text záznamu

Report

A Budget-Adaptive Allocation Rule for Optimal Computing Budget Allocation

Autor: Cao, Zirui, Wang, Haowei, Chew, Ek Peng, Li, Haobin, Tan, Kok Choon

Simulation-based ranking and selection (R&S) is a popular technique for optimizing discrete-event systems (DESs). It evaluates the mean performance of system designs by simulation outputs and aims to identify the best system design from a finite set

Externí odkaz: http://arxiv.org/abs/2304.02377

Zobrazit plný text záznamu

Report

Incomplete Multi-view Clustering via Prototype-based Imputation

Autor: Li, Haobin, Li, Yunfan, Yang, Mouxing, Hu, Peng, Peng, Dezhong, Peng, Xi

In this paper, we study how to achieve two characteristics highly-expected by incomplete multi-view clustering (IMvC). Namely, i) instance commonality refers to that within-cluster instances should share a common pattern, and ii) view versatility ref

Externí odkaz: http://arxiv.org/abs/2301.11045

Zobrazit plný text záznamu