<italic>MBMT-Net</italic>: A Multi-Task Learning Based Convolutional Neural Network Architecture for Dense Prediction Tasks

<italic>MBMT-Net</italic>: A Multi-Task Learning Based Convolutional Neural Network Architecture for Dense Prediction Tasks

Recently proposed improvements in the field of Computer Vision refer to enhancing the feature processing capabilities of Single-Task Convolutional Neural Networks. A typical Single-Task network consists of a backbone and a head, where the feature extractor is usually optimised using the gradient pro...

Full description

Bibliographic Details
Main Authors: George Ciubotariu, Gabriela Czibula
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Computer vision
convolutional neural network
depth estimation
multi-backbone
multi-task
semantic segmentation
Online Access:https://ieeexplore.ieee.org/document/9966556/

Internet

https://ieeexplore.ieee.org/document/9966556/

Similar Items