Papers with Code · CC BY-SA 4.0

Universal Domain Adaptation

Domain Adaptation › Universal Domain Adaptation 51 평가 기록 4 datasets

논문

LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

2403.03421 2024-03-06 이 페이지의 평가 3건

H-score: 87.8Source-Free: yes

MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation

2312.07871 2023-12-13 이 페이지의 평가 3건

H-score: 92.8Source-Free: no

Upcycling Models under Domain and Category Shift

2303.07110 2023-03-13 이 페이지의 평가 3건

H-score: 87.8Source-Free: yes

Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier

2023-01-01 이 페이지의 평가 2건

H-score: 91.8Source-Free: no

Domain Consensus Clustering for Universal Domain Adaptation

2021-06-05 이 페이지의 평가 2건

H-score: 80.16Source-Free: no

Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation

2022-01-01 이 페이지의 평가 2건

H-score: 87.6Source-Free: no

Learning to Detect Open Classes for Universal Domain Adaptation

이 페이지의 평가 2건

H-score: 73.14Source-Free: no

OVANet: One-vs-All Network for Universal Domain Adaptation

2104.03344 2021-04-07 이 페이지의 평가 2건

H-score: 86.5Source-Free: no

Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation

2506.03521 2025-06-04 이 페이지의 평가 2건

H-Score: 89.44Source-free: noVLM: yes

UMAD: Universal Model Adaptation under Domain and Category Shift

2112.08553 2021-12-16 이 페이지의 평가 2건

H-score: 87.0Source-Free: yes

Unified Optimal Transport Framework for Universal Domain Adaptation

2210.17067 2022-10-31 이 페이지의 평가 2건

H-score: 91.13Source-Free: no

Universal Domain Adaptation

2019-06-01 이 페이지의 평가 2건

H-score: 63.46Source-Free: no

Universal Domain Adaptation via Compressive Attention Matching

2304.11862 2023-04-24 이 페이지의 평가 2건

H-score: 95.95Source-Free: no

Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation

2002.08546 2020-02-20 이 페이지의 평가 1건

H-Score: 40.7Source-free: yesVLM: no