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/hasibzunair/synthetic-covid-cxr-dataset
공식 코드Synthesis of COVID-19 Chest X-rays using Unpaired Image-to-Image Translation
https://github.com/hdoi5324/benthic-uda
공식 코드Improved Benthic Classification using Resolution Scaling and SymmNet Unsupervised Domain Adaptation
https://github.com/hdvos/euparliamentasrdataandcode
공식 코드Political corpus creation through automatic speech recognition on EU debates
https://github.com/heboyong/Diffusion-Domain-Teacher
공식 코드Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector
https://github.com/hehefan/Unsupervised-Person-Re-identification-Clustering-and-Fine-tuning
공식 코드Unsupervised Person Re-identification: Clustering and Fine-tuning
https://github.com/hehxcf/cpc
공식 코드Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments
https://github.com/helen1c/mc-panda
공식 코드https://github.com/hellowangqian/UDA-norm-VAE
공식 코드Data Augmentation with norm-VAE for Unsupervised Domain Adaptation
https://github.com/hellowangqian/domain-adaptation-capls
공식 코드Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition
https://github.com/hemanthdv/da-hash
공식 코드https://github.com/hf618/dtbs
공식 코드https://github.com/hik-lab/slimda
공식 코드https://github.com/hilab-git/fpl-plus
공식 코드https://github.com/hongbin98/proca
공식 코드Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
https://github.com/hongyouc/idol
공식 코드Gradual Domain Adaptation without Indexed Intermediate Domains
https://github.com/hou-yz/DA_visualization
공식 코드https://github.com/houtan-ghaffari/SSCCSLR
공식 코드An Efficient Method for the Classification of Croplands in Scarce-Label Regions
https://github.com/hritam-98/gfda-disentangled
공식 코드https://github.com/hsinyilin19/discriminator-constrained-optimal-transport-network
공식 코드Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport
https://github.com/hsqmlzno1/Transferable-E2E-ABSA
공식 코드Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning
https://github.com/hugo-oliveira/CoDAGANs
공식 코드Truly Generalizable Radiograph Segmentation with Conditional Domain Adaptation
https://github.com/huitangtang/DADA-AAAI2020
공식 코드https://github.com/huitangtang/H-SRDC
공식 코드https://github.com/huitangtang/SRDC-CVPR2020
공식 코드Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
https://github.com/huitangtang/SRDCPP
공식 코드https://github.com/huitangtang/disclusterda
공식 코드Unsupervised Domain Adaptation via Distilled Discriminative Clustering
https://github.com/hyeonwoocho7/Cell_Detection-MICCAI
공식 코드Cell Detection in Domain Shift Problem Using Pseudo-Cell-Position Heatmap
https://github.com/hyeonwoocho7/UDA-Cell-Detection
공식 코드Effective Pseudo-Labeling based on Heatmap for Unsupervised Domain Adaptation in Cell Detection
https://github.com/idealwei/ASANet
공식 코드Affinity Space Adaptation for Semantic Segmentation Across Domains
https://github.com/ifnspaml/UBNA
공식 코드https://github.com/ifnspaml/cbna
공식 코드Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation
https://github.com/iit-pavis/learnaug-uda
공식 코드Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation
https://github.com/imatif17/Prototype-Mean-Teacher
공식 코드Multi-Source Domain Adaptation for Object Detection with Prototype-based Mean-teacher
https://github.com/inouye-lab/alignment-upper-bound
공식 코드https://github.com/intelligentmachines-itu/domain-adaptive-building-counting
공식 코드Cross-Region Building Counting in Satellite Imagery using Counting Consistency
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.