https://github.com/dyballa/generalization
공식 코드A separability-based approach to quantifying generalization: which layer is best?
Papers with Code 아카이브
Domain Generalization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 21
- 보존된 평가 기록
- 570
The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain
Source: Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/dyu62/deep-domain-generalization
공식 코드https://github.com/dyxu-cuhkcse/smg-learning
공식 코드https://github.com/ecker-lab/robust-bdd
공식 코드Assessing out-of-domain generalization for robust building damage detection
https://github.com/ecreager/eiil
공식 코드https://github.com/eheinert/reducing-texture-bias-of-dnns-via-eed
공식 코드Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion
https://github.com/envision-research/generalizable-bev
공식 코드Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasing
https://github.com/epfl-dlab/invariant-language-models
공식 코드https://github.com/erictan7/tgp-t
공식 코드https://github.com/exathlonbenchmark/divad
공식 코드Unsupervised Anomaly Detection in Multivariate Time Series across Heterogeneous Domains
https://github.com/excitedkid/vipaug
공식 코드https://github.com/explainableml/acvc
공식 코드Attention Consistency on Visual Corruptions for Single-Source Domain Generalization
https://github.com/facebookresearch/ConvNeXt
공식 코드https://github.com/facebookresearch/DomainBed
공식 코드https://github.com/facebookresearch/InvarianceUnitTests
공식 코드Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms
https://github.com/facebookresearch/InvariantRiskMinimization
공식 코드https://github.com/facebookresearch/ModelRatatouille
공식 코드Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
https://github.com/facebookresearch/ResNeXt
공식 코드Aggregated Residual Transformations for Deep Neural Networks
https://github.com/facebookresearch/Whac-A-Mole
공식 코드A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
https://github.com/facebookresearch/XRM
공식 코드https://github.com/facebookresearch/dinov2
공식 코드https://github.com/facebookresearch/icp-block-mdp
공식 코드Learning Domain Invariant Representations in Goal-conditioned Block MDPs
https://github.com/facebookresearch/latent-treelstm
공식 코드https://github.com/facebookresearch/mae
공식 코드https://github.com/facebookresearch/mixup-cifar10
공식 코드https://github.com/facebookresearch/vissl
공식 코드Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
https://github.com/fayeben/adas
공식 코드UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipeline
https://github.com/flagopen/flagembedding
공식 코드Towards A Generalist Code Embedding Model Based On Massive Data Synthesis
https://github.com/fmcarlucci/ADAGE
공식 코드https://github.com/fmcarlucci/JigenDG
공식 코드https://github.com/fmlinks/domain
공식 코드Adaptive Semi-Supervised Segmentation of Brain Vessels with Ambiguous Labels
https://github.com/foreverps/poer
공식 코드https://github.com/fpsluozi/smd-smos-proj
공식 코드https://github.com/francescodisalvo05/medmnistc-api
공식 코드https://github.com/freddieniu/prompt-qa
공식 코드https://github.com/freshman97/csu
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.