Search Results for author: Junshi Xia

Found 8 papers, 2 papers with code

Submeter-level Land Cover Mapping of Japan

no code implementations19 Nov 2023 Naoto Yokoya, Junshi Xia, Clifford Broni-Bediako

Deep learning has shown promising performance in submeter-level mapping tasks; however, the annotation cost of submeter-level imagery remains a challenge, especially when applied on a large scale.

Land Cover Classification

Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing

no code implementations12 Sep 2023 Clifford Broni-Bediako, Junshi Xia, Naoto Yokoya

With the success of efficient deep learning methods (i. e., efficient deep neural networks) for real-time semantic segmentation in computer vision, researchers have adopted these efficient deep neural networks in remote sensing image analysis.

Image Segmentation Real-Time Semantic Segmentation +2

Building Damage Mapping with Self-PositiveUnlabeled Learning

no code implementations4 Nov 2021 Junshi Xia, Naoto Yokoya, Bruno Adriano

Humanitarian organizations must have fast and reliable data to respond to disasters.

Humanitarian

Dynamic Multi-Task Learning for Face Recognition with Facial Expression

1 code implementation8 Nov 2019 Zuheng Ming, Junshi Xia, Muhammad Muzzamil Luqman, Jean-Christophe Burie, Kaixing Zhao

This multi-task learning with dynamic weights also boosts of the performance on the different tasks comparing to the state-of-art methods with single-task learning.

Face Recognition Face Verification +3

FaceLiveNet+: A Holistic Networks For Face Authentication Based On Dynamic Multi-task Convolutional Neural Networks

no code implementations28 Feb 2019 Zuheng Ming, Junshi Xia, Muhammad Muzzamil Luqman, Jean-Christophe Burie, Kaixing Zhao

This paper proposes a holistic multi-task Convolutional Neural Networks (CNNs) with the dynamic weights of the tasks, namely FaceLiveNet+, for face authentication.

Face Verification Facial Expression Recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.