https://github.com/ssi-research/sfda-rchc
공식 코드Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation
Papers with Code 아카이브
Source-Free Domain Adaptation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 7
- 보존된 평가 기록
- 19
Source-Free Domain Adaptation (SFDA) is a domain adaptation method in machine learning and computer vision where the goal is to adapt a pre-trained model to a new, target domain without access to the source domain data. This approach is advantageous in scenarios where sharing the source data is impractical due to privacy concerns, data size, or proprietary restrictions
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/tim-learn/SHOT
공식 코드https://github.com/tim-learn/SHOT-plus
공식 코드Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
https://github.com/tim-learn/awesome-test-time-adaptation
공식 코드A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
https://github.com/tim-learn/geonet23_casia_tim
공식 코드https://github.com/tl-uestc/bi-aten
공식 코드https://github.com/tntek/source-free-domain-adaptation
공식 코드Source-Free Domain Adaptation with Frozen Multimodal Foundation Model
https://github.com/val-iisc/MixupDA
공식 코드Balancing Discriminability and Transferability for Source-Free Domain Adaptation
https://github.com/val-iisc/stickerda
공식 코드Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation
https://github.com/val-iisc/usfda
공식 코드https://github.com/valeoai/ttyd
공식 코드Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation
https://github.com/vibashan/irg-sfda
공식 코드Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection
https://github.com/vs-cv/sf-yolo
공식 코드https://github.com/xmed-lab/dfg
공식 코드https://github.com/xuyu0010/atcon
공식 코드Source-free Video Domain Adaptation by Learning Temporal Consistency for Action Recognition
https://github.com/ygjwd12345/TransDA
공식 코드https://github.com/yihong-97/source-free-iapc
공식 코드https://github.com/yihong-97/source-free_iapc
공식 코드https://github.com/yuhed/proxymix
공식 코드ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
https://github.com/yukilulu/cac
공식 코드Contrast and Clustering: Learning Neighborhood Pair Representation for Source-free Domain Adaptation
https://github.com/yxiwang/atp
공식 코드A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation
https://github.com/zheangh/dfg
공식 코드https://github.com/zhuzhu804/bba
공식 코드https://github.com/zichengpan/eianet
공식 코드https://github.com/zwenyu/colearn-plus
공식 코드Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation
https://github.com/zyezhang/dac
공식 코드Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
https://github.com/Claydon-Wang/OFTTA
https://github.com/Flashkong/Source-Free-Object-Detection-by-Learning-to-Overlook-Domain-Style
https://github.com/INK-USC/DualRE
https://github.com/Lan1991Xu/ONE_NeurIPS2018
https://github.com/RainbowNebula/PETS
Periodically Exchange Teacher-Student for Source-Free Object Detection
https://github.com/ZHKKKe/PixelSSL
https://github.com/albert0147/nrc_sfda
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
https://github.com/benathi/fastswa-semi-sup
https://github.com/davidpengucf/RAIN
RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation
https://github.com/divyakraman/SAfE-Self-Attention-Based-Unsupervised-Road-Safety-Classification-in-Hazardous-Environments
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.