https://github.com/bismex/MetaBIN
공식 코드Meta Batch-Instance Normalization for Generalizable Person Re-Identification
Papers with Code 아카이브
Unsupervised Domain Adaptation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 49
- 보존된 평가 기록
- 393
Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.
Source: Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/bit-da/domain-oriented-transformer
공식 코드Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation
https://github.com/bit-da/eada
공식 코드Active Learning for Domain Adaptation: An Energy-Based Approach
https://github.com/bit-da/o2net
공식 코드Improving Transferability for Domain Adaptive Detection Transformers
https://github.com/bit-da/sepico
공식 코드SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
https://github.com/bit-ml/cshift
공식 코드Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift
https://github.com/bostoncake/c-visdit
공식 코드Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation
https://github.com/boudinfl/silk
공식 코드Unsupervised Domain Adaptation for Keyphrase Generation using Citation Contexts
https://github.com/bplank/awesome-neural-adaptation-in-NLP
공식 코드https://github.com/brdav/cma
공식 코드Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation
https://github.com/brdav/refign
공식 코드Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
https://github.com/bupt-ai-cz/IAST-ECCV2020
공식 코드Instance Adaptive Self-Training for Unsupervised Domain Adaptation
https://github.com/bupt-ai-cz/hiast
공식 코드Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation
https://github.com/bupt-ai-cz/wuda
공식 코드WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels
https://github.com/bzantium/bert-AAD
공식 코드Knowledge Distillation for BERT Unsupervised Domain Adaptation
https://github.com/camma-public/hpe-adaptor
공식 코드https://github.com/camwew/tada-mi
공식 코드https://github.com/canbaoburen/CoDT
공식 코드https://github.com/canqin001/PointDAN
공식 코드PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
https://github.com/caoyu1991/CASe
공식 코드https://github.com/captain-hong/sfuda_aos
공식 코드Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation
https://github.com/cavin-lee/idsp
공식 코드https://github.com/cc-ai/climategan
공식 코드ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
https://github.com/cc-ai/mila-simulated-floods
공식 코드ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
https://github.com/ccc870206/3d-pl
공식 코드3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling
https://github.com/cchen-cc/SIFA
공식 코드https://github.com/cchen-cc/sfda-dpl
공식 코드Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling
https://github.com/ccsasuke/man
공식 코드Multinomial Adversarial Networks for Multi-Domain Text Classification
https://github.com/cdtrans/cdtrans
공식 코드CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
https://github.com/chaneyddtt/UDA-Animal-Pose
공식 코드From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
https://github.com/chaytonmin/occupancy-mae
공식 코드https://github.com/chaytonmin/voxel-mae
공식 코드https://github.com/chen742/DCF
공식 코드Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation
https://github.com/chen742/PiPa
공식 코드PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
https://github.com/chenchao666/HoMM-Master
공식 코드HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation
https://github.com/chenhao2345/ABMT
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.