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/jh-oh-23/sup-ancl
공식 코드On the Effectiveness of Supervision in Asymmetric Non-Contrastive Learning
https://github.com/jhoon-cho/mbtl
공식 코드Model-Based Transfer Learning for Contextual Reinforcement Learning
https://github.com/jhyuklee/DensePhrases
공식 코드https://github.com/jiaconghu/model-lego
공식 코드Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
https://github.com/jiadongzh/iacos
공식 코드iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examples
https://github.com/jiajunzhou96/polycl
공식 코드https://github.com/jianbojiao/awcl
공식 코드Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound
https://github.com/jianguda/afm4acs
공식 코드https://github.com/jianhongbai/bacon
공식 코드Towards Distribution-Agnostic Generalized Category Discovery
https://github.com/jiaqihuang01/detris
공식 코드Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation
https://github.com/jiasenlu/visDial.pytorch
공식 코드https://github.com/jiaweihhuang/rlhf_rewardtransfer
공식 코드Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
https://github.com/jiaweihhuang/robust-tiered-rl
공식 코드https://github.com/jiayou-chao/multi-domain-ocr
공식 코드Efficient Multi-domain Text Recognition Deep Neural Network Parameterization with Residual Adapters
https://github.com/jichan3751/ifca
공식 코드https://github.com/jieshibo/petl-vit
공식 코드Convolutional Bypasses Are Better Vision Transformer Adapters
https://github.com/jiez-osu/QQC
공식 코드Adversarial Training for Code Retrieval with Question-Description Relevance Regularization
https://github.com/jihanyang/AFN
공식 코드Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
https://github.com/jind11/MMM-MCQA
공식 코드MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension
https://github.com/jinda-liu/r-lora
공식 코드R-LoRA: Random Initialization of Multi-Head LoRA for Multi-Task Learning
https://github.com/jindongli-ai/survey_on_clip-powered_domain_generalization_and_adaptation
공식 코드CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
https://github.com/jindongwang/transferlearning
공식 코드Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning
https://github.com/jinglinglingling/x4d
공식 코드https://github.com/jingyi0000/vlm_survey
공식 코드https://github.com/jinhualiang/apt
공식 코드Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities
https://github.com/jinxhy/smartappattack
공식 코드Smart App Attack: Hacking Deep Learning Models in Android Apps
https://github.com/jinyan-06/shike
공식 코드Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
https://github.com/jishengbai/audiolog
공식 코드AudioLog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning
https://github.com/jitinkrishnan/Crisis-Tweet-Multi-Task-DA
공식 코드Unsupervised and Interpretable Domain Adaptation to Rapidly Filter Tweets for Emergency Services
https://github.com/jixuan-wang/grad2task
공식 코드Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
https://github.com/jjgo/hyperlight
공식 코드Magnitude Invariant Parametrizations Improve Hypernetwork Learning
https://github.com/jjjymmm/refhcm
공식 코드RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios
https://github.com/jjzha/kompetencer
공식 코드https://github.com/jkli1998/drm
공식 코드Leveraging Predicate and Triplet Learning for Scene Graph Generation
https://github.com/jlianglab/benchmarktransferlearning
공식 코드A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.