https://github.com/cpjku/scalearn
공식 코드ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale
Papers with Code 아카이브
Transfer Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 6
- 보존된 평가 기록
- 10
Transfer Learning is a machine learning technique where a model trained on one task is re-purposed and fine-tuned for a related, but different task. The idea behind transfer learning is to leverage the knowledge learned from a pre-trained model to solve a new, but related problem. This can be useful in situations where there is limited data available to train a new model from scratch, or when the new task is similar enough to the original task that the pre-trained model can be adapted to the new problem with only minor modifications.
<span style="color:grey; opacity: 0.6">( Image credit: Subodh Malgonde )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/cplab/annolid
공식 코드https://github.com/cpphoo/STARTUP
공식 코드Self-training for Few-shot Transfer Across Extreme Task Differences
https://github.com/cps11/catvrnn
공식 코드https://github.com/cqu-isse/Plot2API
공식 코드Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Network
https://github.com/cranial-xix/cagrad
공식 코드https://github.com/crazydemo/facial-attribute-classification-with-graph
공식 코드Exploring Correlations in Multiple Facial Attributes through Graph Attention Network
https://github.com/croitorualin/cbm
공식 코드https://github.com/cross-caps/dnntopology
공식 코드On Characterizing the Evolution of Embedding Space of Neural Networks using Algebraic Topology
https://github.com/cross-lingual-ner/projection-data-transfer-cross-lingual-ner
공식 코드https://github.com/cryptolabinc/hetal
공식 코드HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
https://github.com/cscribano/cerberus
공식 코드CERBERUS: Simple and Effective All-In-One Automotive Perception Model with Multi Task Learning
https://github.com/csguoh/adaptir
공식 코드Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
https://github.com/csguoh/kd-ltr
공식 코드One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer
https://github.com/csgwon/AWS-RL-Env
공식 코드Automated Cloud Provisioning on AWS using Deep Reinforcement Learning
https://github.com/cshwhale/Med3D
공식 코드https://github.com/csj199813/a2net_ecpe
공식 코드Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction
https://github.com/ctom2/latent-space-transform
공식 코드https://github.com/cuhklinlab/elasticC3
공식 코드https://github.com/cuijiaxun/MITC-Project
공식 코드Scalable Multiagent Driving Policies For Reducing Traffic Congestion
https://github.com/cunningham-lab/cb_and_cc
공식 코드The continuous categorical: a novel simplex-valued exponential family
https://github.com/cuong-pv/FAM-KD
공식 코드https://github.com/cuongnn218/regression_transferability
공식 코드https://github.com/cuongvng/melep-ecg
공식 코드MELEP: A Novel Predictive Measure of Transferability in Multi-Label ECG Diagnosis
https://github.com/cuongvng/transfer-learning-ecg-diagnosis
공식 코드https://github.com/curai/curai-research
공식 코드Adding more data does not always help: A study in medical conversation summarization with PEGASUS
https://github.com/currentf/lowrankclone
공식 코드A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
https://github.com/curryyuan/x-trans2cap
공식 코드X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning
https://github.com/cuthalionn/prompter
공식 코드Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation
https://github.com/cv-rits/densemtl
공식 코드DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning
https://github.com/cvai-repo/duality-diagram-similarity
공식 코드https://github.com/cvblab/AI4SkIN_leaderboard
공식 코드Benchmarking histopathology foundation models in a multi-center dataset for skin cancer subtyping
https://github.com/cvdfoundation/google-landmark
공식 코드Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
https://github.com/cvi-szu/linly
공식 코드Dynamic data sampler for cross-language transfer learning in large language models
https://github.com/cvl-umass/ssl-evaluation
공식 코드https://github.com/cvl-umass/task2box
공식 코드Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.