Search Results for author: Hujun Yin

Found 16 papers, 4 papers with code

Sparse Spatial Attention Network for Semantic Segmentation

no code implementations4 Sep 2021 Mengyu Liu, Hujun Yin

The spatial attention mechanism captures long-range dependencies by aggregating global contextual information to each query location, which is beneficial for semantic segmentation.

Semantic Segmentation

Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution

no code implementations21 May 2021 Boyan Xu, Hujun Yin

For image processing applications, the use of graph structures and GCNs have not been fully explored.

Deblurring Image Deblurring +2

3D Vision-guided Pick-and-Place Using Kuka LBR iiwa Robot

no code implementations21 Feb 2021 Hanlin Niu, Ze Ji, Zihang Zhu, Hujun Yin, Joaquin Carrasco

This paper presents the development of a control system for vision-guided pick-and-place tasks using a robot arm equipped with a 3D camera.

Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player

1 code implementation21 Feb 2021 Hanlin Niu, Ze Ji, Farshad Arvin, Barry Lennox, Hujun Yin, Joaquin Carrasco

An efficient training strategy is proposed to allow a robot to learn from both human experience data and self-exploratory data.

reinforcement-learning

CNN-Based Semantic Change Detection in Satellite Imagery

no code implementations10 Jun 2020 Ananya Gupta, Elisabeth Welburn, Simon Watson, Hujun Yin

Graph theory is combined with the CNN output for detecting semantic changes in road networks with OpenStreetMap data.

Change Detection

Deep Learning-based Aerial Image Segmentation with Open Data for Disaster Impact Assessment

no code implementations10 Jun 2020 Ananya Gupta, Simon Watson, Hujun Yin

Experimental results show that pretraining on ImageNet usually improves the segmentation performance for a number of models.

Disaster Response Semantic Segmentation

3D Point Cloud Feature Explanations Using Gradient-Based Methods

no code implementations9 Jun 2020 Ananya Gupta, Simon Watson, Hujun Yin

Driven by the insight that 3D data is inherently sparse, we visualise the features learnt by a voxel-based classification network and show that these features are also sparse and can be pruned relatively easily, leading to more efficient neural networks.

Tree Annotations in LiDAR Data Using Point Densities and Convolutional Neural Networks

no code implementations9 Jun 2020 Ananya Gupta, Jonathan Byrne, David Moloney, Simon Watson, Hujun Yin

The third method is a scaled version of the PointNet++ method and works directly on outdoor point clouds and achieves an F_score of 82. 1% on the ISPRS benchmark dataset, comparable to the state-of-the-art methods but with increased efficiency.

Feature Pyramid Encoding Network for Real-time Semantic Segmentation

1 code implementation18 Sep 2019 Mengyu Liu, Hujun Yin

Although current deep learning methods have achieved impressive results for semantic segmentation, they incur high computational costs and have a huge number of parameters.

Panoptic Segmentation Real-Time Semantic Segmentation

Multi-Temporal Aerial Image Registration Using Semantic Features

no code implementations30 Aug 2019 Ananya Gupta, Yao Peng, Simon Watson, Hujun Yin

A semantic feature extraction method for multitemporal high resolution aerial image registration is proposed in this paper.

Image Registration Semantic Segmentation

Meta-Learning with Warped Gradient Descent

1 code implementation ICLR 2020 Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Francesco Visin, Hujun Yin, Raia Hadsell

On the other hand, approaches that try to control a gradient-based update rule typically resort to computing gradients through the learning process to obtain their meta-gradients, leading to methods that can not scale beyond few-shot task adaptation.

Few-Shot Learning Inductive Bias

Cross Attention Network for Semantic Segmentation

no code implementations25 Jul 2019 Mengyu Liu, Hujun Yin

Specifically, a shallow branch is used to preserve low-level spatial information and a deep branch is employed to extract high-level contextual features.

Semantic Segmentation

Breaking the Activation Function Bottleneck through Adaptive Parameterization

1 code implementation NeurIPS 2018 Sebastian Flennerhag, Hujun Yin, John Keane, Mark Elliot

Standard neural network architectures are non-linear only by virtue of a simple element-wise activation function, making them both brittle and excessively large.

WebCaricature: a benchmark for caricature recognition

no code implementations9 Mar 2017 Jing Huo, Wenbin Li, Yinghuan Shi, Yang Gao, Hujun Yin

In this paper, a new caricature dataset is built, with the objective to facilitate research in caricature recognition.

Caricature Computer Vision +1

Robust Face Recognition with Structural Binary Gradient Patterns

no code implementations1 Jun 2015 Weilin Huang, Hujun Yin

To discover underlying local structures in the gradient domain, we compute image gradients from multiple directions and simplify them into a set of binary strings.

Face Recognition Robust Face Recognition

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