Papers with Code 아카이브

Domain Adaptation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 13
평가표: 58
보존된 평가 기록: 391

Domain Adaptation is the task of adapting models across domains. This is motivated by the challenge where the test and training datasets fall from different data distributions due to some factor. Domain adaptation aims to build machine learning models that can be generalized into a target domain and dealing with the discrepancy across domain distributions.

Further readings:

A Brief Review of Domain Adaptation

<span style="color:grey; opacity: 0.6">( Image credit: Unsupervised Image-to-Image Translation Networks )</span>

코드

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

https://github.com/cwei01/tdss

공식 코드

Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation

https://github.com/cxa9264/confeti

공식 코드

Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation

https://github.com/cxmscb/ATDA

공식 코드

Improving the Generalization of Adversarial Training with Domain Adaptation

https://github.com/cxy1997/DiffuBox

공식 코드

DiffuBox: Refining 3D Object Detection with Point Diffusion

https://github.com/cyang-cityu/MetaCorrection

공식 코드

MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation

https://github.com/cybercore-co-ltd/aicity22-track4

공식 코드

Improving Domain Generalization by Learning without Forgetting: Application in Retail Checkout

https://github.com/cynthpie/synthia_melody

공식 코드

Synthia's Melody: A Benchmark Framework for Unsupervised Domain Adaptation in Audio

https://github.com/cyz-ai/infomin

공식 코드

Scalable Infomin Learning

https://github.com/czjdsg/lmbot

공식 코드

LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detection

https://github.com/czx-li/Concentrate-Attention

공식 코드

Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models

https://github.com/dadung/dge-cda

공식 코드

Assessing Domain Gap for Continual Domain Adaptation in Object Detection

https://github.com/daehankim-korea/visda2022_winner_solution

공식 코드

1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation

https://github.com/daintlab/fewshot-sfda

공식 코드

Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation

https://github.com/daintlab/stochastic_cross_attention

공식 코드

StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention

https://github.com/daiquanyu/AdaGCN

공식 코드

Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolution

https://github.com/daishiresearch/transnext

공식 코드

TransNeXt: Robust Foveal Visual Perception for Vision Transformers

https://github.com/dakingrai/ood-generalization-semantic-boundary-techniques

공식 코드

Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniques

https://github.com/damo-nlp-sg/bgca

공식 코드

Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysis

https://github.com/daniellin94144/test-time-adaptation-asr-suta

공식 코드

Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition

https://github.com/danifranco/em_domain_adaptation

공식 코드

Deep learning based domain adaptation for mitochondria segmentation on EM volumes

https://github.com/daoyuan98/MDDA

공식 코드

Multi-source Distilling Domain Adaptation

https://github.com/darlinginthesv/probabilistic-prototypical-pixel-contrast

공식 코드

Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrast

https://github.com/darrenjkt/SEE-MTDA

공식 코드

See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation

https://github.com/darrenjkt/SEE-VCN

공식 코드

Viewer-Centred Surface Completion for Unsupervised Domain Adaptation in 3D Object Detection

https://github.com/darrenjkt/ms3d

공식 코드

MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detection

https://github.com/data-designer/da

공식 코드

Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment

https://github.com/daveishan/codamal

공식 코드

CodaMal: Contrastive Domain Adaptation for Malaria Detection in Low-Cost Microscopes

https://github.com/davevanveen/radadapt

공식 코드

RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models

https://github.com/davidbrandfonbrener/color-filter-olmo

공식 코드

CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-training

https://github.com/davidpengucf/daf-dg

공식 코드

A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation

https://github.com/davidpengucf/epic

공식 코드

Exploiting Aggregation and Segregation of Representations for Domain Adaptive Human Pose Estimation

https://github.com/davidpengucf/sfdahpe

공식 코드

Source-free Domain Adaptive Human Pose Estimation

https://github.com/davidpujol/SADA

공식 코드

SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization

https://github.com/dawnliu35/dejavu-ratp

공식 코드

DEJA VU: Continual Model Generalization For Unseen Domains

https://github.com/dazhangyu123/HCRPL

공식 코드

Hard Class Rectification for Domain Adaptation

https://github.com/dazhangyu123/ocl

공식 코드

Test-Time Training for Semantic Segmentation with Output Contrastive Loss

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