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/umanlp/socioadapt

공식 코드

On the Limitations of Sociodemographic Adaptation with Transformers

https://github.com/umass-ml4ed/tiktoc

공식 코드

Test Case-Informed Knowledge Tracing for Open-ended Coding Tasks

https://github.com/uobinxiao/semantic_cross_attention_fsl

공식 코드

Semantic Cross Attention for Few-shot Learning

https://github.com/urbanmobility/cslsl

공식 코드

Human Mobility Prediction with Causal and Spatial-constrained Multi-task Network

https://github.com/uyoung-jeong/BoIR

공식 코드

BoIR: Box-Supervised Instance Representation for Multi-Person Pose Estimation

https://github.com/valentinhofmann/geoadaptation

공식 코드

Geographic Adaptation of Pretrained Language Models

https://github.com/valeoai/WoodScape/tree/master/omnidet

공식 코드

Surround-View Cameras based Holistic Visual Perception for Automated Driving

https://github.com/valeoai/radial

공식 코드

Raw High-Definition Radar for Multi-Task Learning

https://github.com/valeriechen/ask-your-humans

공식 코드

Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning

https://github.com/vamzimmer/multitask_seg_placenta

공식 코드

Placenta Segmentation in Ultrasound Imaging: Addressing Sources of Uncertainty and Limited Field-of-View

https://github.com/vandadim/adas_mri

공식 코드

Comparison of single and multitask learning for predicting cognitive decline based on MRI data

https://github.com/vanderschaarlab/mlforhealthlabpub/tree/main/alg/causal_multitask_gaussian_processes_ite

공식 코드

Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes

https://github.com/vanlinlin/auto-wcebleedgen-challenge-version-v2

공식 코드

Divide and Conquer: Grounding a Bleeding Areas in Gastrointestinal Image with Two-Stage Model

https://github.com/varunsingh88/MT-DeepONet

공식 코드

Synergistic Learning with Multi-Task DeepONet for Efficient PDE Problem Solving

https://github.com/vcl3d/cmudrn

공식 코드

Cross-Stitched Multi-task Dual Recursive Networks for Unified Single Image Deraining and Desnowing

https://github.com/veali/mlt-le

공식 코드

MLT-LE: predicting drug-target binding affinity with multi-task residual neural networks

https://github.com/vguptai/Neo-Nvidia-Annotations

공식 코드

Progression Modelling for Online and Early Gesture Detection

https://github.com/vico-uoe/mtpsl

공식 코드

Learning Multiple Dense Prediction Tasks from Partially Annotated Data

https://github.com/viktoraxelsen/cle-tfe

공식 코드

One Train for Two Tasks: An Encrypted Traffic Classification Framework Using Supervised Contrastive Learning

https://github.com/virtuosoresearch/task-modeling

공식 코드

Identification of Negative Transfers in Multitask Learning Using Surrogate Models

https://github.com/vishalned/aircast

공식 코드

AirCast: Improving Air Pollution Forecasting Through Multi-Variable Data Alignment

https://github.com/vita-epfl/bounding-box-prediction

공식 코드

Pedestrian Intention Prediction: A Multi-task Perspective

https://github.com/vita-epfl/causalsim2real

공식 코드

Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations

https://github.com/vita-epfl/detection-attributes-fields

공식 코드

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

https://github.com/vita-group/m3vit

공식 코드

M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

https://github.com/vivikar/central-sulcus-analysis

공식 코드

SYNCS: Synthetic Data and Contrastive Self-Supervised Training for Central Sulcus Segmentation

https://github.com/vlc-robot/polarnet

공식 코드

PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation

https://github.com/vub-dl/SLGrad

공식 코드

Sample-Level Weighting for Multi-Task Learning with Auxiliary Tasks

https://github.com/vuptran/graph-representation-learning

공식 코드

Learning to Make Predictions on Graphs with Autoencoders

https://github.com/vuptran/sesemi

공식 코드

Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning

https://github.com/wOOL/DMTRL

공식 코드

Deep Multi-task Representation Learning: A Tensor Factorisation Approach

https://github.com/wOOL/TNRDMTL

공식 코드

Trace Norm Regularised Deep Multi-Task Learning

https://github.com/waliens/multitask-dipath

공식 코드

Multi-task pre-training of deep neural networks for digital pathology

https://github.com/walkerworldpeace/doge

공식 코드

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

https://github.com/wangcongcong123/crisis-mtl

공식 코드

Transformer-based Multi-task Learning for Disaster Tweet Categorisation

https://github.com/wangxb96/mel

공식 코드

MEL: Efficient Multi-Task Evolutionary Learning for High-Dimensional Feature Selection

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