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/softsys4ai/SCTL
공식 코드https://github.com/soham97/MTL_Weakly_labelled_audio_data
공식 코드Improving weakly supervised sound event detection with self-supervised auxiliary tasks
https://github.com/solennegaucher/hierarchical-transfer-learning-covid19
공식 코드Hierarchical transfer learning with applications for electricity load forecasting
https://github.com/solislemuslab/tropical-stethoscope
공식 코드Classification of animal sounds in a hyperdiverse rainforest using Convolutional Neural Networks
https://github.com/somaminami/DCL
공식 코드https://github.com/songchangwei/suicide-risk-prediction
공식 코드https://github.com/songchenlong/tcplp
공식 코드Semantic-enhanced Co-attention Prompt Learning for Non-overlapping Cross-Domain Recommendation
https://github.com/songlab-cal/gpn
공식 코드https://github.com/songlab-cal/tape
공식 코드https://github.com/sonnguyen129/deep-feature-rotation
공식 코드https://github.com/sooncheer0420/samo_mtl
공식 코드https://github.com/sophiewharrie/causal-similarity-based-hierarchical-bayesian-models
공식 코드https://github.com/sophiewharrie/meta-learning-hierarchical-model-similar-causal-mechanisms
공식 코드https://github.com/sophieyueguo/explainable_action_advising
공식 코드Explainable Action Advising for Multi-Agent Reinforcement Learning
https://github.com/sorobedio/dnnwg
공식 코드https://github.com/soumitri2001/smalldatassl
공식 코드Exploring Self-Supervised Representation Learning For Low-Resource Medical Image Analysis
https://github.com/soumyasanyal/mt-cgcnn
공식 코드https://github.com/soumyaxyz/abstractAnalysis
공식 코드https://github.com/souro/multilingual_text_detoxification
공식 코드https://github.com/space-lab-sk/scss-net
공식 코드SCSS-Net: Solar Corona Structures Segmentation by Deep Learning
https://github.com/spaceuma/marssamplelocalization
공식 코드https://github.com/speech-lab-iitm/decar
공식 코드DECAR: Deep Clustering for learning general-purpose Audio Representations
https://github.com/speech-lab-iitm/delores
공식 코드DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning
https://github.com/speechbrain/speechbrain
공식 코드SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation
https://github.com/spirosmaggioros/ForestFires
공식 코드Wildfire danger prediction optimization with transfer learning
https://github.com/srebuffi/semisup_scarse
공식 코드https://github.com/sreyan88/mmer
공식 코드MMER: Multimodal Multi-task Learning for Speech Emotion Recognition
https://github.com/srsawant34/efficient_instruction_learning
공식 코드https://github.com/ssdut-caiyq/ufg-ncd
공식 코드Novel Class Discovery for Ultra-Fine-Grained Visual Categorization
https://github.com/sseung0703/Knowledge_distillation_via_TF2.0
공식 코드Graph-based Knowledge Distillation by Multi-head Attention Network
https://github.com/sseung0703/SSKD
공식 코드Self-supervised Knowledge Distillation Using Singular Value Decomposition
https://github.com/sseung0703/SSKD_SVD
공식 코드Self-supervised Knowledge Distillation Using Singular Value Decomposition
https://github.com/ssi-research/bayesagg_mtl
공식 코드Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
https://github.com/stan-hua/CytoImageNet
공식 코드CytoImageNet: A large-scale pretraining dataset for bioimage transfer learning
https://github.com/stanford-oval/genie-toolkit
공식 코드Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.