Papers with Code 아카이브
Few-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 12
- 평가표
- 27
- 보존된 평가 기록
- 52
Few-Shot Learning is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation.
Source: Penalty Method for Inversion-Free Deep Bilevel Optimization
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/microsoft/LLMLingua
공식 코드LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
https://github.com/microsoft/ORBIT-Dataset
공식 코드ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
https://github.com/microsoft/banknote-net
공식 코드BankNote-Net: Open dataset for assistive universal currency recognition
https://github.com/microsoft/clues
공식 코드CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
https://github.com/microsoft/list
공식 코드LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners
https://github.com/microsoft/unilm
공식 코드https://github.com/mifei/st-tod
공식 코드Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
https://github.com/mihir3009/in-boxbart
공식 코드In-BoXBART: Get Instructions into Biomedical Multi-Task Learning
https://github.com/mikehuisman/lstm-fewshotlearning-oplstm
공식 코드https://github.com/mikehuisman/subspace-adaptation-prior
공식 코드https://github.com/mikewangwzhl/multitask-finetuning_clip
공식 코드Rethinking Task Sampling for Few-shot Vision-Language Transfer Learning
https://github.com/milanlproc/interpretability-mt-gender-bias
공식 코드https://github.com/mileyan/simple_shot
공식 코드SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
https://github.com/milliemaoo/prompt-position
공식 코드https://github.com/mimbres/SeqSkip
공식 코드Sequential Skip Prediction with Few-shot in Streamed Music Contents
https://github.com/mims-harvard/g-meta
공식 코드https://github.com/mindflow-institue/annotation_free_fewshot
공식 코드Self-supervised Few-shot Learning for Semantic Segmentation: An Annotation-free Approach
https://github.com/mindspore-ai/mindscience/tree/master/MindSPONGE/applications/MEGAProtein
공식 코드https://github.com/minglllli/CLS-RL
공식 코드Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning
https://github.com/minhquanlecs/maskdiff
공식 코드https://github.com/minnesotanlp/eyestyliency
공식 코드https://github.com/mir-mu/coat
공식 코드Can In-context Learners Learn a Reasoning Concept from Demonstrations?
https://github.com/mit-ll/robust-vision-language-finetuning
공식 코드Robust Fine-Tuning of Vision-Language Models for Domain Generalization
https://github.com/mkhodak/ARUBA
공식 코드https://github.com/ml-jku/chef
공식 코드https://github.com/ml-jku/clamp
공식 코드Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language
https://github.com/ml-jku/mhnfs
공식 코드Context-enriched molecule representations improve few-shot drug discovery
https://github.com/ml-jku/subgd
공식 코드Few-Shot Learning by Dimensionality Reduction in Gradient Space
https://github.com/ml4ai/mliis
공식 코드https://github.com/mlfoundations/open_clip
공식 코드LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs
https://github.com/mlvlab/rpo
공식 코드Read-only Prompt Optimization for Vision-Language Few-shot Learning
https://github.com/mmcdermott/comprehensive_MTL_EHR
공식 코드https://github.com/mmoradi-iut/BioGPT-3
공식 코드GPT-3 Models are Poor Few-Shot Learners in the Biomedical Domain
https://github.com/mohammadJaliliTorkamani/Kajal
공식 코드Kajal: Extracting Grammar of a Source Code Using Large Language Models
https://github.com/mohammedsb/dinov2formedical
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.