Papers with Code 아카이브

Multi-Task Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 2
평가표: 8
보존된 평가 기록: 16

Multi-task learning aims to learn multiple different tasks simultaneously while maximizing performance on one or all of the tasks.

<span style="color:grey; opacity: 0.6">( Image credit: Cross-stitch Networks for Multi-task Learning )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/sulaimanvesal/CardiacQuanNet

공식 코드

Spatio-temporal Multi-task Learning for Cardiac MRI Left Ventricle Quantification

https://github.com/sungnyun/cav2vec

공식 코드

Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation

https://github.com/sunnyhelen/jperceiver

공식 코드

JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes

https://github.com/super-shayan/feml

공식 코드

Forecasting Early with Meta Learning

https://github.com/super-shayan/qlinear

공식 코드

Auxiliary Quantile Forecasting with Linear Networks

https://github.com/surrey-nlp/homo_gen

공식 코드

Automatically Generating Chinese Homophone Words to Probe Machine Translation Estimation Systems

https://github.com/susaha/ctrl-uda

공식 코드

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation

https://github.com/sutd-visual-computing-group/KML-Classification

공식 코드

Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning

https://github.com/suu990901/LLaMA-InfoEntropy-Loss

공식 코드

MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models

https://github.com/svishwa/crowdcount-cascaded-mtl

공식 코드

CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting

https://github.com/svrtk/masc-multi-task-segmentation-and-classification

공식 코드

Multi-task learning for joint weakly-supervised segmentation and aortic arch anomaly classification in fetal cardiac MRI

https://github.com/swordcheng/FCSR-GAN

공식 코드

FCSR-GAN: Joint Face Completion and Super-resolution via Multi-task Learning

https://github.com/sylyoung/abaw4-hust-ant

공식 코드

Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challenges

https://github.com/synapse-developpement/DiscEval

공식 코드

A Pragmatics-Centered Evaluation Framework for Natural Language Understanding

https://github.com/synapse-developpement/pragmeval

공식 코드

A Pragmatics-Centered Evaluation Framework for Natural Language Understanding

https://github.com/szzexpoi/rex

공식 코드

REX: Reasoning-aware and Grounded Explanation

https://github.com/talswisa/subtuning

공식 코드

Less is More: Selective Layer Finetuning with SubTuning

https://github.com/tanganke/pareto_set_learning

공식 코드

Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion

https://github.com/tanganke/peta

공식 코드

Parameter Efficient Multi-task Model Fusion with Partial Linearization

https://github.com/tanganke/subspace_fusion

공식 코드

Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion

https://github.com/tanganke/weight-ensembling_moe

공식 코드

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

https://github.com/taoshen58/MaSP

공식 코드

Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

https://github.com/tatigabru/kaggle-rsna

공식 코드

Deep Learning for Automatic Pneumonia Detection

https://github.com/temphero/heronet

공식 코드

HeroNet: A Hybrid Retrieval-Generation Network for Conversational Bots

https://github.com/tencent-ailab/hokoff

공식 코드

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

https://github.com/tencentarc/pi-tuning

공식 코드

$π$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation

https://github.com/tensorflow/mesh

공식 코드

ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning

https://github.com/tensorflow/tensor2tensor

공식 코드

One Model To Learn Them All

https://github.com/th-nuernberg/crisis-tapt-hmc

공식 코드

Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning

https://github.com/thanif/CPL

공식 코드

Camera Calibration through Camera Projection Loss

https://github.com/thanif/Camera-Calibration-through-Camera-Projection-Loss

공식 코드

Camera Calibration through Camera Projection Loss

https://github.com/thennal10/fisher-nodes-merging

공식 코드

Fisher Mask Nodes for Language Model Merging

https://github.com/thetna/medical_image_segmentation

공식 코드

Histogram of Oriented Gradients Meet Deep Learning: A Novel Multi-task Deep Network for Medical Image Semantic Segmentation

https://github.com/thisgame42/hybrid-teacher

공식 코드

Hybrid Dual Mean-Teacher Network With Double-Uncertainty Guidance for Semi-Supervised Segmentation of MRI Scans

https://github.com/thu-coai/CommonsenseStoryGen

공식 코드

A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation

https://github.com/thuccslab/mergeguard

공식 코드

Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.