https://github.com/hpc-lab-koreatech/tie-kd
공식 코드TIE-KD: Teacher-Independent and Explainable Knowledge Distillation for Monocular Depth Estimation
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/hrazhan/sentiment
공식 코드https://github.com/hrlblab/glo-in-one_v2
공식 코드https://github.com/hrluo/topologicalmotionseries
공식 코드https://github.com/hs-yn/daps
공식 코드Dense 2D-3D Indoor Prediction with Sound via Aligned Cross-Modal Distillation
https://github.com/hsb1357173526/dynamic_visual_prompting
공식 코드Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting
https://github.com/hsg-aiml/multizoo-sane
공식 코드The Impact of Model Zoo Size and Composition on Weight Space Learning
https://github.com/hsg-aiml/neurips_2021-weight_space_learning
공식 코드Hyper-Representations for Pre-Training and Transfer Learning
https://github.com/hsg-aiml/neurips_2022-generative_hyper_representations
공식 코드Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights
https://github.com/hsg-aiml/sane
공식 코드Hyper-Representations: Learning from Populations of Neural Networks
https://github.com/hsivan/fosi
공식 코드https://github.com/hsouri/bayesiantransferlearning
공식 코드Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors
https://github.com/hsteude/concept-learning-for-cps
공식 코드Learning Physical Concepts in Cyber-Physical Systems: A Case Study
https://github.com/htang113/multi-task-electronic
공식 코드Multi-task learning for molecular electronic structure approaching coupled-cluster accuracy
https://github.com/htsucml/VQAG
공식 코드End-to-End Video Question-Answer Generation with Generator-Pretester Network
https://github.com/hu64/SpotNet
공식 코드SpotNet: Self-Attention Multi-Task Network for Object Detection
https://github.com/huanghanchi/camrl
공식 코드Curriculum-based Asymmetric Multi-task Reinforcement Learning
https://github.com/huangkun101230/360mtlgeometricestimation
공식 코드Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360° Images
https://github.com/huangyjhust/3D-RU-Net
공식 코드3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
https://github.com/huaqinghe/joined
공식 코드JOINED : Prior Guided Multi-task Learning for Joint Optic Disc/Cup Segmentation and Fovea Detection
https://github.com/huawei-noah/noah-research/tree/master/S3-Training
공식 코드DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization
https://github.com/huawei-noah/noah-research/tree/master/freegbdt
공식 코드Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning
https://github.com/huaxiuyao/GFL
공식 코드https://github.com/huaxiuyao/MetaST
공식 코드Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction
https://github.com/huggingface/swift-coreml-transformers
공식 코드DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/huggingface/transformers
공식 코드DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
https://github.com/huggingface/transformers/blob/main/src/transformers/models/squeezebert/modeling_squeezebert.py
공식 코드SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
https://github.com/huggingface/transformers/tree/master/examples/movement-pruning
공식 코드https://github.com/hugo-oliveira/CoDAGANs
공식 코드Truly Generalizable Radiograph Segmentation with Conditional Domain Adaptation
https://github.com/huhailinguist/ChineseNLIProbing
공식 코드https://github.com/hukla/fedclassavg
공식 코드https://github.com/human-analysis/MUXConv
공식 코드MUXConv: Information Multiplexing in Convolutional Neural Networks
https://github.com/human-analysis/neural-architecture-transfer
공식 코드https://github.com/humanlab/rare-class-AL
공식 코드Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge
https://github.com/humanpose1/MS-SVConv
공식 코드3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning
https://github.com/hummosa/thalamus
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.