https://github.com/stepjam/TecNets
공식 코드Task-Embedded Control Networks for Few-Shot Imitation Learning
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/stomachcold/hctransformers
공식 코드Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
https://github.com/stypoumic/beclr
공식 코드https://github.com/sudraj2002/fsgrasp
공식 코드https://github.com/suhyun777/cvpr23-gap
공식 코드https://github.com/sung-won-kim/teg
공식 코드https://github.com/sungnyun/understanding-cdfsl
공식 코드Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
https://github.com/sungwon-han/featllm
공식 코드Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
https://github.com/sunyue93/rep-learning
공식 코드https://github.com/suvarnak/generativefslcovid
공식 코드Generative Transfer Learning: Covid-19 Classification with a few Chest X-ray Images
https://github.com/symanto-research/active-few-shot-learning
공식 코드https://github.com/symanto-research/few-shot-learning-label-tuning
공식 코드https://github.com/syp2ysy/SVF
공식 코드Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
https://github.com/sz128/few_shot_slot_tagging_and_NER
공식 코드Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
https://github.com/tacju/partimagenet
공식 코드https://github.com/tanay2001/core
공식 코드CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation
https://github.com/tankche1/IDeMe-Net
공식 코드https://github.com/tankche1/Semantic-Feature-Augmentation-in-Few-shot-Learning
공식 코드Multi-level Semantic Feature Augmentation for One-shot Learning
https://github.com/tata1661/FewShotPapers
공식 코드Generalizing from a Few Examples: A Survey on Few-Shot Learning
https://github.com/taveraantonio/pixda
공식 코드Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation
https://github.com/tcbenchstack/tcbench
공식 코드https://github.com/tejasanvekar/gpr-net
공식 코드GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
https://github.com/temu-bsc/gpt3-queries
공식 코드On the Multilingual Capabilities of Very Large-Scale English Language Models
https://github.com/tennisonliu/llambo
공식 코드https://github.com/tensorflow/models
공식 코드https://github.com/thaihungle/NSM
공식 코드https://github.com/theoceancleanup/rivertrashsegmentation
공식 코드Foundation Model or Finetune? Evaluation of few-shot semantic segmentation for river pollution
https://github.com/thinklab-sjtu/awesome-llm4ad
공식 코드LLM4Drive: A Survey of Large Language Models for Autonomous Driving
https://github.com/thu-coai/ppt
공식 코드https://github.com/thudm/longbench
공식 코드LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
https://github.com/thudm/msagpt
공식 코드MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
https://github.com/thunlp/OpenMatch
공식 코드CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search
https://github.com/thunlp/OpenPrompt
공식 코드https://github.com/thunlp/fewrel
공식 코드FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
https://github.com/thunlp/seq2seq-prompt
공식 코드Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models
https://github.com/tian1327/swat
공식 코드Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.