https://github.com/hanlu-nju/revisiting-uml
공식 코드Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
Papers with Code 아카이브
Meta-Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 4
- 보존된 평가 기록
- 13
Meta-learning is a methodology considered with "learning to learn" machine learning algorithms.
<span style="color:grey; opacity: 0.6">( Image credit: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/hanshen95/penalized-bilevel-gradient-descent
공식 코드https://github.com/haoang97/medi
공식 코드Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
https://github.com/haoheliu/dcase_2022_task_5
공식 코드Segment-level Metric Learning for Few-shot Bioacoustic Event Detection
https://github.com/haoliu-cola/cola
공식 코드Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node Tasks
https://github.com/haolsun/WarPI
공식 코드https://github.com/haolsun/api
공식 코드https://github.com/haoni0812/mda
공식 코드https://github.com/haotianxia/SPORTU
공식 코드SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models
https://github.com/haotianxia/sportqa
공식 코드SportQA: A Benchmark for Sports Understanding in Large Language Models
https://github.com/haoyu-r/how-to-manage-tinyml-at-scale
공식 코드On-device Online Learning and Semantic Management of TinyML Systems
https://github.com/harkiratbehl/MetaVOS
공식 코드Meta Learning Deep Visual Words for Fast Video Object Segmentation
https://github.com/hassanmojab/metanli
공식 코드Persian Natural Language Inference: A Meta-learning approach
https://github.com/hayeonlee/help
공식 코드HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning
https://github.com/hazyresearch/h3
공식 코드Hungry Hungry Hippos: Towards Language Modeling with State Space Models
https://github.com/hbchen121/dgreid
공식 코드Style Variable and Irrelevant Learning for Generalizable Person Re-identification
https://github.com/hc495/ICL_Circuit
공식 코드Revisiting In-context Learning Inference Circuit in Large Language Models
https://github.com/hccngu/MLADA
공식 코드Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification
https://github.com/hccngu/meta-sn
공식 코드Meta-Learning Siamese Network for Few-Shot Text Classification
https://github.com/hccngu/metnet
공식 코드Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognition
https://github.com/heekhero/ACSR
공식 코드https://github.com/heethanjan/Feature-Generator-for-FSL
공식 코드https://github.com/henrikmarklund/arm
공식 코드Adaptive Risk Minimization: Learning to Adapt to Domain Shift
https://github.com/henulwy/stbdip
공식 코드Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image Classification
https://github.com/heqin-zhu/uod_universal_oneshot_detection
공식 코드https://github.com/herashi/dml-wcls
공식 코드A Meta-Learning Method for Estimation of Causal Excursion Effects to Assess Time-Varying Moderation
https://github.com/hertin/wavprompt
공식 코드WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models
https://github.com/hexiaoxiao-cs/fedml-knee
공식 코드https://github.com/hhhhedy/gfss-ekt
공식 코드Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer
https://github.com/hicai-zju/gs-meta
공식 코드Graph Sampling-based Meta-Learning for Molecular Property Prediction
https://github.com/hitachi-nlp/backward-llm
공식 코드Acquiring Bidirectionality via Large and Small Language Models
https://github.com/hitachi-rd-cv/Difficulty_Net
공식 코드Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition
https://github.com/hiwonjoon/ICRA2019-Activity-Localize
공식 코드One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video
https://github.com/hiwonjoon/MeRLOT
공식 코드https://github.com/hj-harry/ddip3d
공식 코드Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems
https://github.com/hkunlp/unifiedskg
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.