-
Multi-Task Learning on Cityscapes
The authors used the Cityscapes dataset for their experiments. -
Learning to Branch for Multi-Task Learning
Training multiple tasks jointly in one deep network yields reduced latency during inference and better performance over the single-task counterpart by sharing certain layers of... -
LibMTL: A Python Library for Multi-Task Learning
LibMTL is a comprehensive and extensible library for Multi-Task Learning (MTL). It provides a unified training framework for different settings in MTL and supports many... -
MultiMNIST
MultiMNIST dataset, a multi-task learning version of the MNIST dataset. -
Multi-Task Learning as Multi-Objective Optimization
Multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. -
Multi-Fashion+Multi-MNIST
The dataset used in the paper is a multi-task learning dataset, where the goal is to learn a shared feature extractor and a task-specific predictor for multiple tasks. -
Multi-Task Learning for Federated Classification and Regression
The proposed algorithm allows personalizing the learning model for each participant without sharing the training data and improves the performance, compared to that of the... -
Semisoft Task Clustering for Multi-Task Learning
The proposed STCMTL approach can simultaneously learn an overlapping structure among tasks and perform feature selection. -
A Transformer-Based Deep Learning Approach for Fairly Predicting Post-Liver T...
Liver transplantation is a life-saving procedure for patients with end-stage liver disease. There are two main challenges in liver transplant: finding the best matching patient... -
PASCAL-Context and NYUD-v2 datasets
The PASCAL-Context and NYUD-v2 datasets are used for multi-task learning in dense scene understanding. -
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
Simultaneous speech-to-speech translation with multi-task learning -
Meta-world: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement ...
This paper presents a benchmark and evaluation for multi-task and meta reinforcement learning. -
School dataset
The dataset contains examination scores of 15,362 students from 139 schools in London. -
PASCAL Context
The PASCAL Context dataset is a benchmark for multi-task learning in computer vision. It contains 10103 images with 5 tasks: semantic segmentation, human body part segmentation,... -
Task-Aware Low-Rank Adaptation of Segment Anything Model
The Segment Anything Model (SAM) has been proven to be a powerful foundation model for image segmentation tasks, which is an important task in computer vision. However, the...
