https://github.com/scale-lab/mtlora
공식 코드MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
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/schroeterjulien/midl-2022-segmentation-consistent-lesion-counting
공식 코드https://github.com/schuture/metalr
공식 코드MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging
https://github.com/schwarzsophia/transferring_urban_labels_between_pointclouds
공식 코드https://github.com/sciann/sciann-applications
공식 코드A deep learning framework for solution and discovery in solid mechanics
https://github.com/scientific-computing-nrcn/SimulAI
공식 코드Complete CVDL Methodology for Investigating Hydrodynamic Instabilities
https://github.com/sciosci/cite-worthiness
공식 코드https://github.com/sdimi/Step2heart
공식 코드Learning Generalizable Physiological Representations from Large-scale Wearable Data
https://github.com/sdqesdataset/sdqes_generation
공식 코드https://github.com/sea-lab/hybrid-net
공식 코드Deep State Inference: Toward Behavioral Model Inference of Black-box Software Systems
https://github.com/seanzhuh/awesome-open-vocabulary-detection-and-segmentation
공식 코드A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future
https://github.com/seasonSH/SemanticStyleGAN
공식 코드https://github.com/seba-1511/shapechanger
공식 코드https://github.com/sebastian-hofstaetter/transformer-kernel-ranking
공식 코드Mitigating the Position Bias of Transformer Models in Passage Re-Ranking
https://github.com/sebastianhafner/conturbancd
공식 코드https://github.com/sebastianruder/learn-to-select-data
공식 코드Learning to select data for transfer learning with Bayesian Optimization
https://github.com/sebastianruder/sluice-networks
공식 코드https://github.com/seblutz/JointFormer
공식 코드https://github.com/secilia-cxy/unettfi
공식 코드Learning Robust Precipitation Forecaster by Temporal Frame Interpolation
https://github.com/seekerhuang/harma
공식 코드Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment
https://github.com/sekilab/RoadDamageDetector
공식 코드Transfer Learning-based Road Damage Detection for Multiple Countries
https://github.com/selinakhan/stylistic-MTL-ukiyoe
공식 코드https://github.com/selmiss/gp-tlstgcn
공식 코드https://github.com/sense-x/geomim
공식 코드https://github.com/senyuanya/mmlc
공식 코드https://github.com/seongku-kang/hetcomp_www23
공식 코드Distillation from Heterogeneous Models for Top-K Recommendation
https://github.com/sessionrec/mtd
공식 코드https://github.com/seulkiyeom/LRP_Pruning_toy_example
공식 코드Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
https://github.com/seunghan96/softclt
공식 코드https://github.com/seungheondoh/lp-music-caps
공식 코드https://github.com/seungho-snu/fxsr
공식 코드Flexible Style Image Super-Resolution using Conditional Objective
https://github.com/sflippl/multi-task
공식 코드Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse
https://github.com/sfu-multimedia-lab/mlscic
공식 코드https://github.com/sgoodfriend/rl-algo-impls
공식 코드A Competition Winning Deep Reinforcement Learning Agent in microRTS
https://github.com/sh-src/autodp
공식 코드Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records
https://github.com/sha-lab/duel
공식 코드Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.