Papers with Code 아카이브

Universal Domain Adaptation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 4
보존된 평가 기록: 51

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/Gorilla-Lab-SCUT/UB2DA

공식 코드

On Universal Black-Box Domain Adaptation

https://github.com/RomainMsrd/UniJDOT

공식 코드

Optimal Transport and Adaptive Thresholding for Universal Domain Adaptation on Time Series

https://github.com/Sapphire-356/TASC

공식 코드

Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation

https://github.com/VisionLearningGroup/DANCE

공식 코드

Universal Domain Adaptation through Self Supervision

https://github.com/VisionLearningGroup/OVANet

공식 코드

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

https://github.com/XHomL/COCA

공식 코드

COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation

https://github.com/YanzuoLu/MLNet

공식 코드

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

https://github.com/albert0147/onering

공식 코드

OneRing: A Simple Method for Source-free Open-partial Domain Adaptation

https://github.com/changwxx/uniot-for-unida

공식 코드

Unified Optimal Transport Framework for Universal Domain Adaptation

https://github.com/deepskies/deepastrouda

공식 코드

Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection

https://github.com/heyjoonkim/universal_domain_adaptation_for_nlp

공식 코드

Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP

https://github.com/ispc-lab/glc

공식 코드

Upcycling Models under Domain and Category Shift

https://github.com/ispc-lab/glc-plus

공식 코드

GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

https://github.com/ispc-lab/lead

공식 코드

LEAD: Learning Decomposition for Source-free Universal Domain Adaptation

https://github.com/macderru/hyperdomainnet

공식 코드

HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks

https://github.com/mims-harvard/raincoat

공식 코드

Domain Adaptation for Time Series Under Feature and Label Shifts

https://github.com/pascalschlachter/comet

공식 코드

COMET: Contrastive Mean Teacher for Online Source-Free Universal Domain Adaptation

https://github.com/pascalschlachter/gmm

공식 코드

Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model

https://github.com/pascalschlachter/planalysis

공식 코드

Analysis of Pseudo-Labeling for Online Source-Free Universal Domain Adaptation

https://github.com/silvia1993/HyMOS

공식 코드

Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation

https://github.com/szubing/uniood

공식 코드

Universal Domain Adaptation from Foundation Models: A Baseline Study

https://github.com/tim-learn/SHOT

공식 코드

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

https://github.com/yu1ut/divergence-optimization

공식 코드

Noisy Universal Domain Adaptation via Divergence Optimization for Visual Recognition

https://github.com/zhu-xlab/unida

공식 코드

Universal Domain Adaptation for Remote Sensing Image Scene Classification

https://github.com/zwenyu/UniSSDA

공식 코드

Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias

https://github.com/AlexisGuichemerreCode/survey_hist_wsol_sfda

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

https://github.com/Claydon-Wang/OFTTA

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

https://github.com/Solacex/Domain-Consensus-Clustering

https://github.com/VisionLearningGroup/visda21-dev

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

https://github.com/ispc-lab/bmd

Upcycling Models under Domain and Category Shift

https://github.com/thuml/Calibrated-Multiple-Uncertainties

https://github.com/zangzelin/code_san_share

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.