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/berlino/tensor2struct-public

공식 코드

Learning to Synthesize Data for Semantic Parsing

https://github.com/bethgelab/robustness

공식 코드

Improving robustness against common corruptions by covariate shift adaptation

https://github.com/better-chao/perceptual_abilities_evaluation

공식 코드

Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation

https://github.com/bflashcp3f/procbert

공식 코드

Pre-train or Annotate? Domain Adaptation with a Constrained Budget

https://github.com/bfshi/InfoDrop

공식 코드

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

https://github.com/bghojogh/Fisher-Triplet-Contrastive-Loss

공식 코드

Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks

https://github.com/bghojogh/Histopathology-Magnification-Generalization

공식 코드

Magnification Generalization for Histopathology Image Embedding

https://github.com/bghojogh/Siamese-Network-Histopathology

공식 코드

Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study

https://github.com/bgswaroop/pushpull-conv

공식 코드

PushPull-Net: Inhibition-driven ResNet robust to image corruptions

https://github.com/bhanukamanesha/ramen

공식 코드

Improved RAMEN: Towards Domain Generalization for Visual Question Answering

https://github.com/bigdata-ustc/Zero-1-to-3

공식 코드

Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives

https://github.com/bilel-bj/unsupervised-domain-adaptation-gan

공식 코드

Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial Images

https://github.com/binhuixie/spcl

공식 코드

SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive Learning

https://github.com/biolearning-stadius/chemgrapher-self-rich-labeling

공식 코드

Self-Labeling of Fully Mediating Representations by Graph Alignment

https://github.com/biomedia-mbzuai/condisr

공식 코드

ConDiSR: Contrastive Disentanglement and Style Regularization for Single Domain Generalization

https://github.com/biomedia-mbzuai/dgm-dr

공식 코드

DGM-DR: Domain Generalization with Mutual Information Regularized Diabetic Retinopathy Classification

https://github.com/biomedia-mira/masf

공식 코드

Domain Generalization via Model-Agnostic Learning of Semantic Features

https://github.com/biqiwhu/hssh

공식 코드

Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination

https://github.com/bismex/MetaBIN

공식 코드

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

https://github.com/bit-da/abs

공식 코드

From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection

https://github.com/bit-da/cirl

공식 코드

Causality Inspired Representation Learning for Domain Generalization

https://github.com/bit-da/dcg

공식 코드

Improving Generalization with Domain Convex Game

https://github.com/bit-da/domain-oriented-transformer

공식 코드

Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation

https://github.com/bit-da/duc

공식 코드

Dirichlet-based Uncertainty Calibration for Active Domain Adaptation

https://github.com/bit-da/dusa

공식 코드

Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation

https://github.com/bit-da/eada

공식 코드

Active Learning for Domain Adaptation: An Energy-Based Approach

https://github.com/bit-da/o2net

공식 코드

Improving Transferability for Domain Adaptive Detection Transformers

https://github.com/bit-da/rotta

공식 코드

Robust Test-Time Adaptation in Dynamic Scenarios

https://github.com/bit-da/scda

공식 코드

Semantic Concentration for Domain Adaptation

https://github.com/bit-da/sepico

공식 코드

SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation

https://github.com/bit-da/vblc

공식 코드

VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions

https://github.com/bit-ml/Stylist

공식 코드

Robust Novelty Detection through Style-Conscious Feature Ranking

https://github.com/bit-ml/cshift

공식 코드

Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift

https://github.com/bit-ml/dupin

공식 코드

Rethinking the Authorship Verification Experimental Setups

https://github.com/blackecho/LoAd-Network

공식 코드

Adaptive Deep Learning through Visual Domain Localization

https://github.com/blindauth/labelshiftexperiments

공식 코드

Maximum Likelihood with Bias-Corrected Calibration is Hard-To-Beat at Label Shift Adaptation

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