no code implementations • 4 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.
no code implementations • 21 May 2021 • Boyan Xu, Hujun Yin
For image processing applications, the use of graph structures and GCNs have not been fully explored.
no code implementations • 8 Mar 2021 • Tian Meng, Yang Tao, Ziqi Chen, Jorge R. Salas Avila, Qiaoye Ran, Yuchun Shao, Ruochen Huang, Yuedong Xie, Qian Zhao, Zhijie Zhang, Hujun Yin, Anthony J. Peyton, Wuliang Yin
Eddy current testing (ECT) is an effective technique in the evaluation of the depth of metal surface defects.
1 code implementation • 21 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.
no code implementations • 21 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.
no code implementations • 10 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.
no code implementations • 10 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.
no code implementations • 9 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.
no code implementations • 9 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.
2 code implementations • 18 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.
no code implementations • 30 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.
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.
1 code implementation • 25 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.
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.
no code implementations • 9 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.
no code implementations • 1 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.