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/ashishgupta2598/sacti

공식 코드

A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit

https://github.com/astra-vision/densemtl

공식 코드

DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning

https://github.com/astra-vision/stablemtl

공식 코드

StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets

https://github.com/atapour/temporal-depth-segmentation

공식 코드

Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach

https://github.com/autumn9999/hnps

공식 코드

Episodic Multi-Task Learning with Heterogeneous Neural Processes

https://github.com/autumn9999/vmtl

공식 코드

Variational Multi-Task Learning with Gumbel-Softmax Priors

https://github.com/avic3nna/joint-mtl-cpath

공식 코드

Joint multi-task learning improves weakly-supervised biomarker prediction in computational pathology

https://github.com/avivnavon/nash-mtl

공식 코드

Multi-Task Learning as a Bargaining Game

https://github.com/aws/aws-refcocog-adv

공식 코드

Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions

https://github.com/axedge1983/li

공식 코드

Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server

https://github.com/ayaanzhaque/MultiMix

공식 코드

Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data

https://github.com/azencot-group/mtlinear

공식 코드

A Multi-Task Learning Approach to Linear Multivariate Forecasting

https://github.com/baijiong-lin/awesome-multi-objective-deep-learning

공식 코드

Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond

https://github.com/baijiong-lin/forum

공식 코드

A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization

https://github.com/baithebest/srdml

공식 코드

Saliency-Regularized Deep Multi-Task Learning

https://github.com/baiyimeng/gradcraft

공식 코드

GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting

https://github.com/bhpfelix/MTLNAS

공식 코드

MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning

https://github.com/bigscience-workshop/biomedical

공식 코드

BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing

https://github.com/bilalghanem/let-mi

공식 코드

Let-Mi: An Arabic Levantine Twitter Dataset for Misogynistic Language

https://github.com/bingrao/ctin

공식 코드

CTIN: Robust Contextual Transformer Network for Inertial Navigation

https://github.com/biomedia-mira/atmil

공식 코드

Multiple Instance Learning with Auxiliary Task Weighting for Multiple Myeloma Classification

https://github.com/birlrobotics/rlkit_autotune

공식 코드

Hyperparameter Auto-tuning in Self-Supervised Robotic Learning

https://github.com/bit-ml/cshift

공식 코드

Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift

https://github.com/bloomberg/dataless-model-merging

공식 코드

Dataless Knowledge Fusion by Merging Weights of Language Models

https://github.com/bojesomo/Traffic4Cast2020-DeepSedanionNetwork

공식 코드

Traffic flow prediction using Deep Sedenion Networks

https://github.com/bowenc0221/Decoupled-Classification-Refinement

공식 코드

Decoupled Classification Refinement: Hard False Positive Suppression for Object Detection

https://github.com/bplank/DaNplus

공식 코드

DaN+: Danish Nested Named Entities and Lexical Normalization

https://github.com/bplank/semi-supervised-baselines

공식 코드

Strong Baselines for Neural Semi-supervised Learning under Domain Shift

https://github.com/brozosc/graph-neural-networks-for-surfactant-multi-property-prediction

공식 코드

Graph Neural Networks for Surfactant Multi-Property Prediction

https://github.com/brunotruthalliance/resflow

공식 코드

Residual Multi-Task Learner for Applied Ranking

https://github.com/bumble666/hypermoe_early_version

공식 코드

HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts

https://github.com/bumble666/pha

공식 코드

Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning

https://github.com/bundlerecommender/bundlemage

공식 코드

Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters

https://github.com/burakekim/MTL_homoscedastic_SRB

공식 코드

A Multi-Task Deep Learning Framework for Building Footprint Segmentation

https://github.com/byeongjun-park/DTR

공식 코드

Denoising Task Routing for Diffusion Models

https://github.com/byeongjun-park/Switch-DiT

공식 코드

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts

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