paper-with-me

Papers

Consistent Assistant Domains Transformer for Source-free Domain Adaptation

2025-10-02 · Renrong Shao, Wei Zhang, Kangyang Luo, Qin Li, and Jun Wang arxiv

Source-free domain adaptation (SFDA) aims to address the challenge of adapting to a target domain without accessing the source domain directly. However, due to the inaccessibility of source domain data, deterministic invariable features cannot be obtained. Current mainstream methods primarily focus on evaluating invariant features in the target domain that closely resemble those in the source domain, subsequently aligning the target domain with the source domain. However, these methods are susceptible to hard samples and influenced by domain bias. In this paper, we propose a Consistent Assistant Domains Transformer for SFDA, abbreviated as CADTrans, which solves the issue by constructing invariable feature representations of domain consistency. Concretely, we develop an assistant domain module for CADTrans to obtain diversified representations from the intermediate aggregated global attentions, which addresses the limitation of existing methods in adequately representing diversity. Based on assistant and target domains, invariable feature representations are obtained by multiple consistent strategies, which can be used to distinguish easy and hard samples. Finally, to align the hard samples to the corresponding easy samples, we construct a conditional multi-kernel max mean discrepancy (CMK-MMD) strategy to distinguish between samples of the same category and those of different categories. Extensive experiments are conducted on various benchmarks such as Office-31, Office-Home, VISDA-C, and DomainNet-126, proving the significant performance improvements achieved by our proposed approaches. Code is available at https://github.com/RoryShao/CADTrans.git.

📄 PDF Abstract BibTeX arXiv:2510.01559

Code (0)

등록된 구현이 없습니다.

Tasks

Source-Free Domain Adaptation

Similar Papers 제목 키워드 기반

Zero-Resource Hallucination Prevention for Large Language Models

2023-09-06 · Junyu Luo, Cao Xiao, Fenglong Ma

The prevalent use of large language models (LLMs) in various domains has drawn attention to the issue of "hallucination," which refers to instances where LLMs generate factually inaccurate or ungrounded information. Exis…

Hallucination

Transformer-based Model for ASR N-Best Rescoring and Rewriting

2024-06-12 · Iwen E. Kang, Christophe Van Gysel, Man-Hung Siu

Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on the device, queries pertaining to complex information domains often requ…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

A Comparison of Strategies for Source-Free Domain Adaptation

2021-08-17 · ACL ARR August 2021 8 · Anonymous

Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free…

Active LearningData AugmentationDomain AdaptationSource-Free Domain Adaptation

A Comparison of Strategies for Source-Free Domain Adaptation

2022-05-01 · ACL 2022 5 · Xin Su, Yiyun Zhao, Steven Bethard

Data sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, a setting known as source-free…

Active LearningData AugmentationDomain AdaptationSource-Free Domain Adaptation

RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain

2024-03-21 · William James Bolton, Rafael Poyiadzi, Edward R. Morrell, Gabriela van Bergen Gonzalez Bueno 외

Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. I…

Semantic SimilaritySemantic Textual Similarity