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/AbhinavAtrishi/semisupervised-multitask-learning
UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation
https://github.com/AdamStein97/Semi-Supervised-BERT-NER
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
https://github.com/AhmedYounes94/Semi-supervised-BERT-NER
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
https://github.com/Alexander-H-Liu/End-to-end-ASR-Pytorch
Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning
https://github.com/AmirMoMo/COVID-19
https://github.com/Andy1314Chen/PaddleRec
https://github.com/Andyeyeye/MTANet
Facial Affect Recognition in the Wild Using Multi-Task Learning Convolutional Network
https://github.com/ArenCarpenter/Covid_CT_Classification
https://github.com/AshishMehtaIO/MTLfD-CARLA
Learning End-to-end Autonomous Driving using Guided Auxiliary Supervision
https://github.com/BIT-aerial-robotics/AquaML/blob/2.1.11/AquaML/rlalgo/COPGAgent.py
Clipped-Objective Policy Gradients for Pessimistic Policy Optimization
https://github.com/BITCS-Information-Retrieval-2020/search-rattailcollagen1
Encoding Visual Attributes in Capsules for Explainable Medical Diagnoses
https://github.com/Bala93/Multi-task-deep-network
Conv-MCD: A Plug-and-Play Multi-task Module for Medical Image Segmentation
https://github.com/Bangbangbanana/fairmot_mindspore
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
https://github.com/Ben-USC/covid-19-USCD
https://github.com/BorealisAI/DynaShare-MTL
AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
https://github.com/CAVED123/METAWORLD
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
https://github.com/CLUEbenchmark/CLUE
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
https://github.com/CMU-Perceptual-Computing-Lab/openpose_caffe_train
https://github.com/COMP6248-Reproducability-Challenge/COMP6248-Self-Supervised-Generalisation-with-Meta-Auxiliary-Learning
https://github.com/CXMANDTXW/MTL-Using-Uncertainty-to-Weigh-Losses
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
https://github.com/CalumPerrio/WNUT-2020
https://github.com/CharlieDinh/FedU_FMTL
A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularization
https://github.com/Cirhuzalain/cdsmodel
https://github.com/CubiCasa/CubiCasa5k
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
https://github.com/Danil328/RetinaFace
RetinaFace: Single-stage Dense Face Localisation in the Wild
https://github.com/Danyache/skoltech_image_cap
https://github.com/Dasol-Choi/DLFD
https://github.com/DataScienceNigeria/ALBERT-for-Natural-Language-Processing
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
https://github.com/DataScienceNigeria/ERNIE-2.0-from-Baidu-Inc.
ERNIE 2.0: A Continual Pre-training Framework for Language Understanding
https://github.com/DataXujing/YOLOR-
You Only Learn One Representation: Unified Network for Multiple Tasks
https://github.com/DomhnallBoyle/sv2s
Lip-to-Speech Synthesis in the Wild with Multi-task Learning
https://github.com/Duan-JM/awesome-papers-fewshot
https://github.com/EbnulMahmood/PatternLab
Deep Learning for Patient-Specific Kidney Graft Survival Analysis
https://github.com/EdNiehues/simulacao-de-projeto-para-mapeamento
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
https://github.com/EightRice/atn_GPT-3
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.