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/Telecommunication-Telemedia-Assessment/ai_upscaling
공식 코드https://github.com/Tencent/MedicalNet
공식 코드https://github.com/Tencent/TFace
공식 코드Evaluation-oriented Knowledge Distillation for Deep Face Recognition
https://github.com/Tencent/tencent-ml-images
공식 코드Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning
https://github.com/TencentYoutuResearch/EventExtraction-RAAT
공식 코드https://github.com/TheMVS/DL_AD_mri_sex_age_stages
공식 코드Automatic Assessment of Alzheimer's Disease Diagnosis Based on Deep Learning Techniques
https://github.com/Tianyihu212/Materarbeit
공식 코드Content-Based Landmark Retrieval Combining Global and Local Features using Siamese Neural Networks
https://github.com/TokisakiKurumi2001/UniBridge
공식 코드UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages
https://github.com/Tombs98/SU-Net
공식 코드SU-Net: Pose estimation network for non-cooperative spacecraft on-orbit
https://github.com/TripHawkers/OM-real-time-inference
공식 코드https://github.com/TzorAL/transfer-learning-forecasting
공식 코드https://github.com/UBC-NLP/araT5
공식 코드AraT5: Text-to-Text Transformers for Arabic Language Generation
https://github.com/UBC-NLP/microdialects
공식 코드Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments
https://github.com/UCI-ISA-Lab/MultiHeadDepth-HomoDepth
공식 코드Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses
https://github.com/UIC-Liu-Lab/ContinualLM
공식 코드https://github.com/UKPLab/acl2017-neural_end2end_AM
공식 코드Neural End-to-End Learning for Computational Argumentation Mining
https://github.com/UKPLab/acl2020-dialogue-coherence-assessment
공식 코드Dialogue Coherence Assessment Without Explicit Dialogue Act Labels
https://github.com/UKPLab/acl2021-label-suggestions-german-covid19
공식 코드Investigating label suggestions for opinion mining in German Covid-19 social media
https://github.com/UKPLab/mdl-stance-robustness
공식 코드Stance Detection Benchmark: How Robust Is Your Stance Detection?
https://github.com/UKPLab/naacl18-multitask_argument_mining
공식 코드Multi-Task Learning for Argumentation Mining in Low-Resource Settings
https://github.com/UKPLab/sentence-transformers
공식 코드Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
https://github.com/UMBCvision/ISD
공식 코드ISD: Self-Supervised Learning by Iterative Similarity Distillation
https://github.com/UlysseCoteAllard/LongTermEMG
공식 코드https://github.com/UniLauX/AINet
공식 코드https://github.com/UtsaChattopadhyay/MSAI/blob/main/SourceCode%20for%20low%20Resource%20MT.zip
공식 코드https://github.com/VADERASU/visual-analytics-for-deep-transfer-learning
공식 코드A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes
https://github.com/VALUE-Leaderboard/StarterCode
공식 코드VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
https://github.com/VICO-UoE/KD4MTL
공식 코드https://github.com/VIPriors/vipriors-challenges-toolkit
공식 코드VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
https://github.com/VITA-Group/LightGaussian
공식 코드LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
https://github.com/VITA-MLLM/VITA
공식 코드https://github.com/VRCMF/MARN
공식 코드Multitask Balanced and Recalibrated Network for Medical Code Prediction
https://github.com/VRCMF/MT-RAM
공식 코드Multitask Balanced and Recalibrated Network for Medical Code Prediction
https://github.com/VainF/Data-Free-Adversarial-Distillation
공식 코드https://github.com/Valentyn1997/oct-diagn-semi-supervised
공식 코드Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.