https://github.com/yangyangxu0/mqtransformer
공식 코드Multi-Task Learning with Multi-Query Transformer for Dense Prediction
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/yangyuwenyang/Codes-for-Deep-Transfer-Learning-Based-Downlink-Channel-Prediction-for-FDD-Massive-MIMO-Systems
공식 코드Deep Transfer Learning Based Downlink Channel Prediction for FDD Massive MIMO Systems
https://github.com/yankd22/calm
공식 코드CALM: Consensus-Aware Localized Merging for Multi-Task Learning
https://github.com/yanqidai/igb4mtl
공식 코드https://github.com/yanyuanqiao/vln-petl
공식 코드VLN-PETL: Parameter-Efficient Transfer Learning for Vision-and-Language Navigation
https://github.com/yaoching0/gac
공식 코드https://github.com/yaoyao-liu/meta-transfer-learning
공식 코드https://github.com/yaoyueduzhen/HomOTL-ODDM
공식 코드Homogeneous Online Transfer Learning with Online Distribution Discrepancy Minimization
https://github.com/yaserkl/TransferRL
공식 코드https://github.com/yaxingwang/DeepI2I
공식 코드DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs
https://github.com/yaxingwang/MineGAN
공식 코드MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains
https://github.com/yaxirhuxxain/TransferLearning
공식 코드https://github.com/ychen-stat-ml/kernel-adapters
공식 코드https://github.com/ydup/Anomaly-Detection-in-Time-Series-with-Triadic-Motif-Fields
공식 코드https://github.com/ydup/bokeh
공식 코드https://github.com/ydyordanov/few-shot-nles
공식 코드Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup
https://github.com/yeliudev/R2-Tuning
공식 코드R^2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding
https://github.com/yeongseoj/conkd
공식 코드https://github.com/yeonsw/BLANC
공식 코드https://github.com/yeppp27/q-adapt
공식 코드Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning
https://github.com/yewen1486/emtal
공식 코드Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning
https://github.com/yezilaixi/kt-rcnet
공식 코드Knowledge Transfer-Driven Few-Shot Class-Incremental Learning
https://github.com/yf-he/unigraph2
공식 코드UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs
https://github.com/yfchen1994/poisoning_membership
공식 코드https://github.com/yfchen1994/teacher-fingerprinting
공식 코드Teacher Model Fingerprinting Attacks Against Transfer Learning
https://github.com/yhygao/universal-medical-image-segmentation
공식 코드Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation
https://github.com/yibowang214/multiner
공식 코드Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach
https://github.com/yichaolu/traffic4cast2021
공식 코드Learning to Transfer for Traffic Forecasting via Multi-task Learning
https://github.com/yichiac/crop-type-transfer-learning
공식 코드On the Generalizability of Foundation Models for Crop Type Mapping
https://github.com/yifanycc/loretta
공식 코드https://github.com/yifanzhang-pro/matrix-llm
공식 코드https://github.com/yifanzhang-pro/matrix-ssl
공식 코드https://github.com/yifei-he/excessmtl
공식 코드https://github.com/yifei-he/localize-and-stitch
공식 코드Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
https://github.com/yifei-liu-stat/pass
공식 코드Perturbation-Assisted Sample Synthesis: A Novel Approach for Uncertainty Quantification
https://github.com/yifei-liu-stat/syn
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.