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/ufsccosmos/psfgan-gamornet
공식 코드https://github.com/uhh-lt/hatespeech
공식 코드How Hateful are Movies? A Study and Prediction on Movie Subtitles
https://github.com/uhh-pd-ml/omnijet_alpha
공식 코드OmniJet-$α$: The first cross-task foundation model for particle physics
https://github.com/uic-liu-lab/spg
공식 코드https://github.com/uicdice/imm-logistic-regression
공식 코드Induced Model Matching: How Restricted Models Can Help Larger Ones
https://github.com/uiuctml/TaskVectorBasis
공식 코드Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach
https://github.com/uiuctml/localize-and-stitch
공식 코드Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
https://github.com/ukplab/emnlp2020-multicqa
공식 코드MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale
https://github.com/ukplab/iclr2024-model-merging
공식 코드https://github.com/ukplab/naacl2024-fun
공식 코드https://github.com/ulyssegazin/TransductiveAdaptive_CP
공식 코드https://github.com/um2ii/quantum-cxr
공식 코드https://github.com/umair-nasir14/ngdc
공식 코드https://github.com/umanlp/socioadapt
공식 코드On the Limitations of Sociodemographic Adaptation with Transformers
https://github.com/umass-ml4ed/tiktoc
공식 코드Test Case-Informed Knowledge Tracing for Open-ended Coding Tasks
https://github.com/umbc-sanjaylab/favtGAN
공식 코드Generating Thermal Human Faces for Physiological Assessment Using Thermal Sensor Auxiliary Labels
https://github.com/umbertocappellazzo/petl_ast
공식 코드Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
https://github.com/umgupta/2d-slice-set-networks
공식 코드Transferring Models Trained on Natural Images to 3D MRI via Position Encoded Slice Models
https://github.com/uniadapter/uniadapter
공식 코드UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
https://github.com/unibas-gravis/parametric-face-image-generator
공식 코드https://github.com/unifyid-labs/DeepGenStruct-Notebooks
공식 코드Fonts-2-Handwriting: A Seed-Augment-Train framework for universal digit classification
https://github.com/unity-technologies/peoplesanspeople
공식 코드PeopleSansPeople: A Synthetic Data Generator for Human-Centric Computer Vision
https://github.com/unza-speech-lab/zambezi-voice
공식 코드Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages
https://github.com/uobinxiao/semantic_cross_attention_fsl
공식 코드https://github.com/urbanmobility/cslsl
공식 코드Human Mobility Prediction with Causal and Spatial-constrained Multi-task Network
https://github.com/uri-abd/clam
공식 코드Clustered Hierarchical Anomaly and Outlier Detection Algorithms
https://github.com/usc-sail/child-adult-diarization
공식 코드Data Efficient Child-Adult Speaker Diarization with Simulated Conversations
https://github.com/ussiamaboat/polytuplet-loss
공식 코드Deep Manifold Learning for Reading Comprehension and Logical Reasoning Tasks with Polytuplet Loss
https://github.com/ussiamaboat/research-paper
공식 코드Deep Manifold Learning for Reading Comprehension and Logical Reasoning Tasks with Polytuplet Loss
https://github.com/uta-smile/TVT
공식 코드TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
https://github.com/utiasSTARS/cat-net
공식 코드https://github.com/utiasstars/lfgp
공식 코드https://github.com/utrerf/robust_transfer_learning
공식 코드Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification
https://github.com/uts-caslab/sps-quality
공식 코드https://github.com/uvavision/chair-segments
공식 코드Chair Segments: A Compact Benchmark for the Study of Object Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.