https://github.com/virtualspaceman/transfer-estimation-medical
공식 코드The Performance of Transferability Metrics does not Translate to Medical Tasks
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/virtuosoresearch/ml4roadsafety
공식 코드Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
https://github.com/virtuosoresearch/robust-fine-tuning
공식 코드Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
https://github.com/virtuosoresearch/task-modeling
공식 코드Identification of Negative Transfers in Multitask Learning Using Surrogate Models
https://github.com/vishaldeyiiest/graphta
공식 코드Enhancing Molecular Property Prediction with Auxiliary Learning and Task-Specific Adaptation
https://github.com/vishalned/aircast
공식 코드AirCast: Improving Air Pollution Forecasting Through Multi-Variable Data Alignment
https://github.com/vision4robotics/sam-da
공식 코드SAM-DA: UAV Tracks Anything at Night with SAM-Powered Domain Adaptation
https://github.com/visionlearninggroup/uda_poseestimation
공식 코드https://github.com/visipedia/imat_fashion_comp
공식 코드https://github.com/visipedia/newt
공식 코드Benchmarking Representation Learning for Natural World Image Collections
https://github.com/vita-epfl/bounding-box-prediction
공식 코드https://github.com/vita-epfl/causalmotion
공식 코드Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective
https://github.com/vita-epfl/causalsim2real
공식 코드https://github.com/vita-epfl/detection-attributes-fields
공식 코드https://github.com/vita-epfl/motion-style-transfer
공식 코드Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting
https://github.com/vita-group/double-win-lth
공식 코드Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
https://github.com/vita-group/m3vit
공식 코드https://github.com/vitae-transformer/aptv2
공식 코드APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond
https://github.com/vivikar/central-sulcus-analysis
공식 코드SYNCS: Synthetic Data and Contrastive Self-Supervised Training for Central Sulcus Segmentation
https://github.com/vlbthambawita/MedicoTask_2019_paper_2
공식 코드Extracting temporal features into a spatial domain using autoencoders for sperm video analysis
https://github.com/vlc-robot/polarnet
공식 코드PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation
https://github.com/voidmagic/parameter-differentiation
공식 코드Parameter Differentiation based Multilingual Neural Machine Translation
https://github.com/vpgtrans/vpgtrans
공식 코드https://github.com/vpulab/synthmanticlidar
공식 코드SynthmanticLiDAR: A Synthetic Dataset for Semantic Segmentation on LiDAR Imaging
https://github.com/vsuarezpaniagua/3-phase_finetuning
공식 코드Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models
https://github.com/vt-nlp/multiinstruct
공식 코드MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning
https://github.com/vub-dl/SLGrad
공식 코드Sample-Level Weighting for Multi-Task Learning with Auxiliary Tasks
https://github.com/vul337/callee
공식 코드Callee: Recovering Call Graphs for Binaries with Transfer and Contrastive Learning
https://github.com/vuptran/graph-representation-learning
공식 코드https://github.com/vuptran/sesemi
공식 코드Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning
https://github.com/w-lw/pclc
공식 코드https://github.com/wOOL/DMTRL
공식 코드Deep Multi-task Representation Learning: A Tensor Factorisation Approach
https://github.com/wOOL/TNRDMTL
공식 코드https://github.com/waliens/multitask-dipath
공식 코드Multi-task pre-training of deep neural networks for digital pathology
https://github.com/walkerworldpeace/doge
공식 코드Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
https://github.com/wangangcheng/lora-pt
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.