Papers with Code 아카이브

cross-domain few-shot learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 1
보존된 평가 기록: 1

Its essence is transfer learning. The model needs to be trained in the source domain and then migrated to the target domain. Compliant with (1) the category in the target domain has never appeared in the source domain (2) the data distribution of the target domain is inconsistent with the source domain (3) each class in the target domain has very few labels

코드

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

https://github.com/Alibaba-AAIG/SSL-FEW-SHOT

공식 코드

Self-Supervised Learning For Few-Shot Image Classification

https://github.com/VICO-UoE/URL

공식 코드

Cross-domain Few-shot Learning with Task-specific Adapters

https://github.com/YangYongJin/APEX

공식 코드

Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning

https://github.com/Zhen-ao/BSDB-CDFSL_Track

공식 코드

Ensemble Model with Batch Spectral Regularization and Data Blending for Cross-Domain Few-Shot Learning with Unlabeled Data

https://github.com/asrafulashiq/dynamic-cdfsl

공식 코드

Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data

https://github.com/bbbdylan/unisiam

공식 코드

Self-Supervision Can Be a Good Few-Shot Learner

https://github.com/debabratapal7/dafosnet

공식 코드

Domain Adaptive Few-Shot Open-Set Learning

https://github.com/frkl/modular-adaptation

공식 코드

Modular Adaptation for Cross-Domain Few-Shot Learning

https://github.com/google-research/meta-dataset

공식 코드

Cross-domain Few-shot Learning with Task-specific Adapters

https://github.com/henulwy/stbdip

공식 코드

Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image Classification

https://github.com/hongyujerrywang/featureextractorstacking

공식 코드

Feature Extractor Stacking for Cross-domain Few-shot Learning

https://github.com/icvteam/dara

공식 코드

Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning

https://github.com/johncai117/DAMSL

공식 코드

DAMSL: Domain Agnostic Meta Score-based Learning

https://github.com/lisuyi/pbadv_czsl

공식 코드

Contextual Interaction via Primitive-based Adversarial Training For Compositional Zero-shot Learning

https://github.com/lovelyqian/ME-D2N_for_CDFSL

공식 코드

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

https://github.com/lovelyqian/Meta-FDMixup

공식 코드

Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data

https://github.com/lovelyqian/styleadv-cdfsl

공식 코드

StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning

https://github.com/lovelyqian/wave-SAN-CDFSL

공식 코드

Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning

https://github.com/ml-jku/chef

공식 코드

Cross-Domain Few-Shot Learning by Representation Fusion

https://github.com/naeem-paeedeh/adapter

공식 코드

Cross-Domain Few-Shot Learning via Adaptive Transformer Networks

https://github.com/ondrejbohdal/evograd

공식 코드

EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization

https://github.com/open-debin/bayesian_mqda

공식 코드

Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

https://github.com/qityy/droppatch

공식 코드

Enhancing Masked Time-Series Modeling via Dropping Patches

https://github.com/rashindrie/dipa

공식 코드

Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning

https://github.com/sarinda251/cdfsl-v

공식 코드

CDFSL-V: Cross-Domain Few-Shot Learning for Videos

https://github.com/sungnyun/understanding-cdfsl

공식 코드

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty

https://github.com/tinkez/fap_cdfsc

공식 코드

Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Prompting

https://github.com/tomte812/chef

공식 코드

Cross-Domain Few-Shot Learning by Representation Fusion

https://github.com/vico-uoe/universalrepresentations

공식 코드

Universal Representations: A Unified Look at Multiple Task and Domain Learning

https://github.com/xuhuali-mxj/im-dcl

공식 코드

Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning

https://github.com/xuhuali-mxj/stepspt

공식 코드

Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning

https://github.com/zoilsen/flor

공식 코드

Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning

https://github.com/zouxinyi0625/cdnet

공식 코드

Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition

https://github.com/2023-MindSpore-1/ms-code-217/tree/main/unisiam

Self-Supervision Can Be a Good Few-Shot Learner

https://github.com/Dipeshtamboli/Cross-Domain-FSL-via-NSAE

Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder

https://github.com/IBM/cdfsl-benchmark

A Broader Study of Cross-Domain Few-Shot Learning

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