https://github.com/HyeonwooNoh/vqa_task_discovery
공식 코드Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
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/HzFu/COVID19_imaging_AI_paper_list
공식 코드Towards Data-Efficient Learning: A Benchmark for COVID-19 CT Lung and Infection Segmentation
https://github.com/Hzzone/MTLFace
공식 코드When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework
https://github.com/I2-Multimedia-Lab/A2S-v3
공식 코드Unified Unsupervised Salient Object Detection via Knowledge Transfer
https://github.com/IBM/Contrastive-Explanation-Method
공식 코드https://github.com/IBM/TRAIL
공식 코드https://github.com/IBM/bridging-resolution
공식 코드https://github.com/IBM/geostats-gen-error
공식 코드https://github.com/IBM/transition-amr-parser
공식 코드https://github.com/ICHISubmission/Metric-Breast-Cancer
공식 코드https://github.com/IDU-CVLab/COV19D_2nd
공식 코드COVID-19 Detection Using Transfer Learning Approach from Computed Tomography Images
https://github.com/IMSY-DKFZ/self-distilled-swin
공식 코드https://github.com/IMSY-DKFZ/task-fingerprinting
공식 코드Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AI
https://github.com/INK-USC/CLIF
공식 코드Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning
https://github.com/IPL-UV/pvl8dagans
공식 코드Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V images for Cloud Detection
https://github.com/IST-DASLab/sparseprop
공식 코드SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks
https://github.com/IljaManakov/WalkingTheTightrope
공식 코드Walking the Tightrope: An Investigation of the Convolutional Autoencoder Bottleneck
https://github.com/Information-Fusion-Lab-Umass/causal_transfer_learning
공식 코드https://github.com/Inha-CVAI/MADGNet
공식 코드https://github.com/InnerPeas/ML-for-Transaction-Costs
공식 코드https://github.com/Inpyo-Hong/AKT-Advanced-knowledge-Transfer
공식 코드https://github.com/IntelVCL/MultiObjectiveOptimization
공식 코드https://github.com/IoBT-VISTEC/MetaSleepLearner
공식 코드https://github.com/It4innovations/urban_change_monitoring_mariupol_ua
공식 코드Monitoring of Urban Changes with multi-modal Sentinel 1 and 2 Data in Mariupol, Ukraine, in 2022/23
https://github.com/JBall1/Few-Shot-Limited-Data
공식 코드https://github.com/JBall1/Food101-CNN
공식 코드Food Classification with Convolutional Neural Networks and Multi-Class Linear Discernment Analysis
https://github.com/JH-GEECS/CART_public
공식 코드https://github.com/JLDeng/ST-Norm
공식 코드A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting
https://github.com/JLiangLab/SemanticGenesis
공식 코드https://github.com/JLiangLab/TransVW
공식 코드https://github.com/JRC1995/Tweet-Disaster-Keyphrase
공식 코드https://github.com/JStehouwer/FFD_CVPR2020
공식 코드https://github.com/JWSoh/MZSR
공식 코드https://github.com/JWoong148/MetaPerturb
공식 코드MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
https://github.com/Jack-Poole/Statistic-Alignment
공식 코드On statistic alignment for domain adaptation in structural health monitoring
https://github.com/Jacob-Zhou/stack-parser
공식 코드Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.