15 datasets found

The authors used the Cityscapes dataset for their experiments.

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...

The MNIST-Fellowship dataset is composed of three datasets (MNIST, Fashion-MNIST, and KMNIST) each composed of 10 classes.

Anomaly detection in video via self-supervised and 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 dataset, a multi-task learning version of the MNIST dataset.

Multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them.

The dataset used in the paper is a Chinese education pre-trained language model BERTEdu and a large education domain corpus of all structural exercise database.

Change detection (CD) methods have been applied to optical data for decades, while the use of hyperspectral data with a fine spectral resolution has been rarely explored. CD is...

The folktables dataset contains information about the mobility and income of individuals in California, with a sensitive feature of gender.

Aff-Wild2 is a large-scale in-the-wild database for affective behavior analysis, containing 564 videos with frame-level annotations for valence-arousal estimation, facial action...

This paper presents a benchmark and evaluation for multi-task and meta reinforcement learning.

The dataset contains examination scores of 15,362 students from 139 schools in London.

The proposed model was evaluated on the fMRI dataset we collected from healthy subjects. In the fMRI experiment, subjects were asked to imagine and listen to four categories...

A multi-task learning framework for emotion recognition and facial image generation