https://github.com/harshs27/uglad
공식 코드uGLAD: Sparse graph recovery by optimizing deep unrolled networks
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/harvard-edge/multilingual_kws
공식 코드https://github.com/hasibzunair/adversarial-lesions
공식 코드Melanoma Detection using Adversarial Training and Deep Transfer Learning
https://github.com/hassanmojab/metanli
공식 코드Persian Natural Language Inference: A Meta-learning approach
https://github.com/hassounlab/boost-rs
공식 코드https://github.com/hassyGo/charNgram2vec
공식 코드A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
https://github.com/hazyresearch/wonderbread
공식 코드https://github.com/hchoi71/mix-kd
공식 코드Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study
https://github.com/hclent/creoleval
공식 코드https://github.com/hduc-le/simcpsr
공식 코드SimCPSR: Simple Contrastive Learning for Paper Submission Recommendation System
https://github.com/he-h/HuMob
공식 코드https://github.com/heboyong/Generalized-Diffusion-Detector
공식 코드https://github.com/hecoding/hyper-modulation
공식 코드Transferring Unconditional to Conditional GANs with Hyper-Modulation
https://github.com/hecta-uom/clinicalnmt
공식 코드https://github.com/heekhero/DTL
공식 코드https://github.com/hehe91/LA
공식 코드Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach
https://github.com/heimine/pnc_dln
공식 코드Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
https://github.com/hellowangqian/cdspp-hda
공식 코드Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation
https://github.com/helme/ecg_ptbxl_benchmarking
공식 코드Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL
https://github.com/hemanthdv/da-hash
공식 코드https://github.com/hendrycks/test
공식 코드https://github.com/hengxyz/Dynamic_multi-task-learning
공식 코드Dynamic Multi-Task Learning for Face Recognition with Facial Expression
https://github.com/hengxyz/cari-visual-recognition-via-multitask-learning
공식 코드Dynamic Deep Multi-task Learning for Caricature-Visual Face Recognition
https://github.com/henrygouk/mars-finetuning
공식 코드Distance-Based Regularisation of Deep Networks for Fine-Tuning
https://github.com/heraclex12/VLSP2020-Fake-News-Detection
공식 코드Leveraging Transfer Learning for Reliable Intelligence Identification on Vietnamese SNSs (ReINTEL)
https://github.com/heraldoborges/tuxkconfig
공식 코드Linux Kernel Configurations at Scale: A Dataset for Performance and Evolution Analysis
https://github.com/herolab-uga/KTBT-Release
공식 코드KT-BT: A Framework for Knowledge Transfer Through Behavior Trees in Multi-Robot Systems
https://github.com/hesam-92-19/transfer_learning_shm
공식 코드https://github.com/hessaalawwad/plr-tqa
공식 코드https://github.com/heyzude/bmtpt
공식 코드Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning
https://github.com/hf618/dtbs
공식 코드https://github.com/hfawaz/bigdata18
공식 코드https://github.com/hfawaz/dl-4-tsc
공식 코드https://github.com/hfawaz/miccai18
공식 코드https://github.com/hgilles06/infashai
공식 코드Neural Fashion Image Captioning : Accounting for Data Diversity
https://github.com/hguimaraes/robustdistiller
공식 코드An Efficient End-to-End Approach to Noise Invariant Speech Features via Multi-Task Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.