Aug 2026· Multimedia Systems· Vol 32· 0 citations· 50 references
TL;DR
A Peer-level Heterogeneous Perception Framework is proposed that departs from such paradigms by enabling balanced collaboration between heterogeneous models by introducing an auxiliary domain that is significantly different from the target domain and employ an auxiliary model with the same architecture as the source model, thereby eliminating capacity bias while preserving heterogeneity.
COSMO replaces expert-to-expert guidance with co-adaptation through an anchored shared consensus and achieves state-of-the-art performance under matched VLM backbones, indicating that it better balances the retention of valid source-derived evidence with the absorption of complementary VLM evidence.
Bo Li, Junjie Peng, Xiaohua Xie et al.· 0 citations
This work proposes a novel criterion, termed Maximum Refinement Decision score (MRD-score), which replaces softmax with median centering to normalize source models’ predictions along both positive and negative axes, thereby harnessing both affirmative and complementary guidance.
Bing-Tao Zhou, Mian Xiang, Qian Ning· Journal of King Saud Univers...· 0 citations
This paper proposes ADA-CS, a plug-and-play module compatible with any ADA or ASFDA framework, and introduces a CSS metric to quantify the Concept Shift Severity across domains, revealing that non-negligible concept shift exists in many transfer tasks.
This paper proposes a novel SFDA with high-confidence sample selection and feature disentanglement for machinery fault diagnosis, which effectively alleviates the adverse influence of noisy pseudo-labels during the stage of adaptation.
Yi-Ming Yuan, Kang Wu, Xing-Xing Jiang et al.· Measurement science and tech...· 0 citations
Black-box unsupervised domain adaptation (black-box UDA) aims to adapt a target model without accessing source data or source-model parameters. Compared with conventional unsupervised domain adaptation (UDA) and source-free UDA (SFUDA), this setting better protects data privacy and model security, but poses greater cha...
Wei Li, Wenyi Zhao, Lianlei Shan et al.· IEEE Transactions on Neural...· 0 citations
